chrome-devtools-mcp-v1.5.0
497 次代码提交
| 作者 | SHA1 | 备注 | 提交日期 | |
|---|---|---|---|---|
 browser-automation-bot
|
913308263b |
chore(main): release chrome-devtools-mcp 1.5.0 (#2252)
publish-on-tag / publish-to-npm (push) Has been cancelled
publish-on-tag / publish-to-mcp-registry (push) Has been cancelled
🤖 I have created a release *beep* *boop* --- ## [1.5.0](https://github.com/ChromeDevTools/chrome-devtools-mcp/compare/chrome-devtools-mcp-v1.4.0...chrome-devtools-mcp-v1.5.0) (2026-07-03) ### 🎉 Features * Add get_heapsnapshot_duplicate_strings MCP tool ([#2280](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/2280)) ([ |
||
|
Dominik Inführ
|
67a56c0557 |
feat: Add get_heapsnapshot_duplicate_strings MCP tool (#2280)
This PR adds a new MCP tool to find duplicated strings in the heap snapshot. Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> |
||
|
Trung Huynh Chi
|
a9228141ae |
fix: validate extension-enforced output paths (#2269)
Fixes output path validation so tools cannot validate one path and then write to a different canonical target after extension enforcement. Changes: - Resolve dangling symlinks to their target path during canonicalization. - Validate the final extension-enforced output path before writing. - Apply the same final-path validation to heap snapshots and screencasts. - Add regression coverage for dangling symlinks that point outside configured roots. Validation: - npm run format - npm run check-format - npm run test tests/utils/files.test.ts - npm run test tests/roots.test.ts - npm run test tests/tools/memory.test.ts tests/tools/screencast.test.ts Note: I also ran the full npm test suite locally. The targeted tests above passed, but the full suite hit local WSL daemon/e2e startup timeouts while waiting for daemon.pid / server_start, which appear unrelated to this path-validation change. --------- Co-authored-by: huynhtrungcsc <huynhtrungcsc@users.noreply.github.com> |
||
|
yasirusman85
|
cf00305170 |
fix(cli): improve error messages to guide AI agents and developers (#2161)
Co-authored-by: Nicholas Roscino <nroscino@google.com> Co-authored-by: Piotr Paulski <31672205+zyzyzyryxy@users.noreply.github.com> Co-authored-by: Piotr Paulski <piotrpaulski@chromium.org> |
||
|
Dominik Inführ
|
3f4a49a89a |
refactor: Merge MCP tools for comparing heap snapshots (#2281)
Instead of two separate MCP tools, we can have one instead which takes classIndex as optional argument. Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> |
||
|
Piotr Paulski
|
8d8cf1299d |
docs: fix formatting and indentation of tool descriptions (#2275)
Follow-up on formatting changes introduced by dependency update in #2266 Co-authored-by: Piotr Paulski <piotrpaulski@chromium.org> |
||
|
dependabot[bot]
|
ce5edbd6a3 |
chore(deps-dev): bump the dev-dependencies group across 1 directory with 7 updates (#2266)
Bumps the dev-dependencies group with 7 updates in the / directory: | Package | From | To | | --- | --- | --- | | [@google/genai](https://github.com/googleapis/js-genai) | `2.9.0` | `2.10.0` | | [@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node) | `26.0.0` | `26.0.1` | | [@typescript-eslint/eslint-plugin](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/eslint-plugin) | `8.61.1` | `8.62.0` | | [@typescript-eslint/parser](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/parser) | `8.61.1` | `8.62.0` | | [globals](https://github.com/sindresorhus/globals) | `17.6.0` | `17.7.0` | | [prettier](https://github.com/prettier/prettier) | `3.8.4` | `3.9.3` | | [typescript-eslint](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/typescript-eslint) | `8.61.1` | `8.62.0` | Updates `@google/genai` from 2.9.0 to 2.10.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/googleapis/js-genai/releases">@google/genai's releases</a>.</em></p> <blockquote> <h2>v2.10.0</h2> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.9.0...v2.10.0">2.10.0</a> (2026-06-24)</h2> <h3>Features</h3> <ul> <li>[Interactions] Add ComputerUse.disabled_safety_policies (<a href="https://github.com/googleapis/js-genai/commit/a2ca95cb81230ac371864914d2ad655c3f83c7bb">a2ca95c</a>)</li> <li>[Models] Add ComputerUse.disabled_safety_policies (<a href="https://github.com/googleapis/js-genai/commit/3618023147fe8ba63a9ecfa00253ab489e74aba8">3618023</a>)</li> <li>add usage fields for steps (<a href="https://github.com/googleapis/js-genai/commit/048db9a660d6cb7107212baab64e694db8498dfc">048db9a</a>)</li> <li>add video generation and response format parameters. (<a href="https://github.com/googleapis/js-genai/commit/84e795cf4add4ca9dffe47828d6528e19d684d54">84e795c</a>)</li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/googleapis/js-genai/blob/main/CHANGELOG.md">@google/genai's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.9.0...v2.10.0">2.10.0</a> (2026-06-24)</h2> <h3>Features</h3> <ul> <li>[Interactions] Add ComputerUse.disabled_safety_policies (<a href="https://github.com/googleapis/js-genai/commit/a2ca95cb81230ac371864914d2ad655c3f83c7bb">a2ca95c</a>)</li> <li>[Models] Add ComputerUse.disabled_safety_policies (<a href="https://github.com/googleapis/js-genai/commit/3618023147fe8ba63a9ecfa00253ab489e74aba8">3618023</a>)</li> <li>add usage fields for steps (<a href="https://github.com/googleapis/js-genai/commit/048db9a660d6cb7107212baab64e694db8498dfc">048db9a</a>)</li> <li>add video generation and response format parameters. (<a href="https://github.com/googleapis/js-genai/commit/84e795cf4add4ca9dffe47828d6528e19d684d54">84e795c</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/googleapis/js-genai/commit/31223a3e02a5d1c8146ad2673df5a1c7e4bababb"><code>31223a3</code></a> chore(main): release 2.10.0 (<a href="https://redirect.github.com/googleapis/js-genai/issues/1725">#1725</a>)</li> <li><a href="https://github.com/googleapis/js-genai/commit/628f3f2e83202fc040cbc502e98108689489be69"><code>628f3f2</code></a> chore: Disable ComputerUse.disabled_safety_policies in Gemini Enterprise API</li> <li><a href="https://github.com/googleapis/js-genai/commit/84e795cf4add4ca9dffe47828d6528e19d684d54"><code>84e795c</code></a> feat: add video generation and response format parameters.</li> <li><a href="https://github.com/googleapis/js-genai/commit/048db9a660d6cb7107212baab64e694db8498dfc"><code>048db9a</code></a> feat: add usage fields for steps</li> <li><a href="https://github.com/googleapis/js-genai/commit/a2ca95cb81230ac371864914d2ad655c3f83c7bb"><code>a2ca95c</code></a> feat: Add ComputerUse.disabled_safety_policies</li> <li><a href="https://github.com/googleapis/js-genai/commit/3618023147fe8ba63a9ecfa00253ab489e74aba8"><code>3618023</code></a> feat: Add ComputerUse.disabled_safety_policies</li> <li><a href="https://github.com/googleapis/js-genai/commit/eeee71122760ddba9df72611a013c1bd78fc0d7d"><code>eeee711</code></a> docs: fix typos across docstrings</li> <li><a href="https://github.com/googleapis/js-genai/commit/a12a590062760dd75899dc3c28564d3ae62bf67a"><code>a12a590</code></a> chore: Upgrade stalebot action to use v10 (due to Node20 deprecation)</li> <li>See full diff in <a href="https://github.com/googleapis/js-genai/compare/v2.9.0...v2.10.0">compare view</a></li> </ul> </details> <br /> Updates `@types/node` from 26.0.0 to 26.0.1 <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/node">compare view</a></li> </ul> </details> <br /> Updates `@typescript-eslint/eslint-plugin` from 8.61.1 to 8.62.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/typescript-eslint/typescript-eslint/releases">@typescript-eslint/eslint-plugin's releases</a>.</em></p> <blockquote> <h2>v8.62.0</h2> <h2>8.62.0 (2026-06-22)</h2> <h3>🚀 Features</h3> <ul> <li>remove redundant package.json "files" (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12444">#12444</a>)</li> </ul> <h3>🩹 Fixes</h3> <ul> <li>add "files" to rule-schema-to-typescript-types (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12441">#12441</a>)</li> </ul> <h3>❤️ Thank You</h3> <ul> <li>Kirk Waiblinger <a href="https://github.com/kirkwaiblinger"><code>@kirkwaiblinger</code></a></li> </ul> <p>See <a href="https://github.com/typescript-eslint/typescript-eslint/releases/tag/v8.62.0">GitHub Releases</a> for more information.</p> <p>You can read about our <a href="https://typescript-eslint.io/users/versioning">versioning strategy</a> and <a href="https://typescript-eslint.io/users/releases">releases</a> on our website.</p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/eslint-plugin/CHANGELOG.md">@typescript-eslint/eslint-plugin's changelog</a>.</em></p> <blockquote> <h2>8.62.0 (2026-06-22)</h2> <h3>🚀 Features</h3> <ul> <li>remove redundant package.json "files" (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12444">#12444</a>)</li> </ul> <h3>❤️ Thank You</h3> <ul> <li>Kirk Waiblinger <a href="https://github.com/kirkwaiblinger"><code>@kirkwaiblinger</code></a></li> </ul> <p>See <a href="https://github.com/typescript-eslint/typescript-eslint/releases/tag/v8.62.0">GitHub Releases</a> for more information.</p> <p>You can read about our <a href="https://typescript-eslint.io/users/versioning">versioning strategy</a> and <a href="https://typescript-eslint.io/users/releases">releases</a> on our website.</p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/typescript-eslint/typescript-eslint/commit/54e285728e5d8cb83fadb8041189f0c3b4ab436a"><code>54e2857</code></a> chore(release): publish 8.62.0</li> <li><a href="https://github.com/typescript-eslint/typescript-eslint/commit/81e4c2654c3f4d923766a888691add2c45b5d64a"><code>81e4c26</code></a> feat: remove redundant package.json "files" (<a href="https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/eslint-plugin/issues/12444">#12444</a>)</li> <li><a href="https://github.com/typescript-eslint/typescript-eslint/commit/b784054b6f8fbb51eb742304852b37b0436a8a58"><code>b784054</code></a> chore: use <code>stableTypeOrdering</code> compiler option (<a href="https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/eslint-plugin/issues/12427">#12427</a>)</li> <li>See full diff in <a href="https://github.com/typescript-eslint/typescript-eslint/commits/v8.62.0/packages/eslint-plugin">compare view</a></li> </ul> </details> <br /> Updates `@typescript-eslint/parser` from 8.61.1 to 8.62.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/typescript-eslint/typescript-eslint/releases">@typescript-eslint/parser's releases</a>.</em></p> <blockquote> <h2>v8.62.0</h2> <h2>8.62.0 (2026-06-22)</h2> <h3>🚀 Features</h3> <ul> <li>remove redundant package.json "files" (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12444">#12444</a>)</li> </ul> <h3>🩹 Fixes</h3> <ul> <li>add "files" to rule-schema-to-typescript-types (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12441">#12441</a>)</li> </ul> <h3>❤️ Thank You</h3> <ul> <li>Kirk Waiblinger <a href="https://github.com/kirkwaiblinger"><code>@kirkwaiblinger</code></a></li> </ul> <p>See <a href="https://github.com/typescript-eslint/typescript-eslint/releases/tag/v8.62.0">GitHub Releases</a> for more information.</p> <p>You can read about our <a href="https://typescript-eslint.io/users/versioning">versioning strategy</a> and <a href="https://typescript-eslint.io/users/releases">releases</a> on our website.</p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/parser/CHANGELOG.md">@typescript-eslint/parser's changelog</a>.</em></p> <blockquote> <h2>8.62.0 (2026-06-22)</h2> <h3>🚀 Features</h3> <ul> <li>remove redundant package.json "files" (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12444">#12444</a>)</li> </ul> <h3>❤️ Thank You</h3> <ul> <li>Kirk Waiblinger <a href="https://github.com/kirkwaiblinger"><code>@kirkwaiblinger</code></a></li> </ul> <p>See <a href="https://github.com/typescript-eslint/typescript-eslint/releases/tag/v8.62.0">GitHub Releases</a> for more information.</p> <p>You can read about our <a href="https://typescript-eslint.io/users/versioning">versioning strategy</a> and <a href="https://typescript-eslint.io/users/releases">releases</a> on our website.</p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/typescript-eslint/typescript-eslint/commit/54e285728e5d8cb83fadb8041189f0c3b4ab436a"><code>54e2857</code></a> chore(release): publish 8.62.0</li> <li><a href="https://github.com/typescript-eslint/typescript-eslint/commit/81e4c2654c3f4d923766a888691add2c45b5d64a"><code>81e4c26</code></a> feat: remove redundant package.json "files" (<a href="https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/parser/issues/12444">#12444</a>)</li> <li>See full diff in <a href="https://github.com/typescript-eslint/typescript-eslint/commits/v8.62.0/packages/parser">compare view</a></li> </ul> </details> <br /> Updates `globals` from 17.6.0 to 17.7.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/sindresorhus/globals/releases">globals's releases</a>.</em></p> <blockquote> <h2>v17.7.0</h2> <ul> <li>Update globals (2026-06-22) (<a href="https://redirect.github.com/sindresorhus/globals/issues/345">#345</a>) 33b75f9</li> </ul> <hr /> <p><a href="https://github.com/sindresorhus/globals/compare/v17.6.0...v17.7.0">https://github.com/sindresorhus/globals/compare/v17.6.0...v17.7.0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/sindresorhus/globals/commit/a19670cc86c1218e915657c55ea02ba3e7623834"><code>a19670c</code></a> 17.7.0</li> <li><a href="https://github.com/sindresorhus/globals/commit/9611620bad0ea45531ae0261b986ce694374e42c"><code>9611620</code></a> Update actions (<a href="https://redirect.github.com/sindresorhus/globals/issues/346">#346</a>)</li> <li><a href="https://github.com/sindresorhus/globals/commit/33b75f9ddeb6f9ddd81251b043667eb8104a8d15"><code>33b75f9</code></a> Update globals (2026-06-22) (<a href="https://redirect.github.com/sindresorhus/globals/issues/345">#345</a>)</li> <li><a href="https://github.com/sindresorhus/globals/commit/887dd529bde24486b7f9e31d1b2c515df2b7cf5c"><code>887dd52</code></a> Fix build script (<a href="https://redirect.github.com/sindresorhus/globals/issues/344">#344</a>)</li> <li>See full diff in <a href="https://github.com/sindresorhus/globals/compare/v17.6.0...v17.7.0">compare view</a></li> </ul> </details> <br /> Updates `prettier` from 3.8.4 to 3.9.3 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/prettier/prettier/releases">prettier's releases</a>.</em></p> <blockquote> <h2>3.9.3</h2> <ul> <li>Markdown: Fix unexpected removal of characters in liquid syntax (<a href="https://redirect.github.com/prettier/prettier/pull/19489">prettier/prettier#19489</a> by <a href="https://github.com/seiyab"><code>@seiyab</code></a>)</li> <li>TypeScript: Allow decorators to be used with declare on class fields (<a href="https://redirect.github.com/prettier/prettier/pull/19492">prettier/prettier#19492</a> by <a href="https://github.com/evoactivity"><code>@evoactivity</code></a>)</li> </ul> <p>🔗 <a href="https://github.com/prettier/prettier/blob/3.9.3/CHANGELOG.md#393">Changelog</a></p> <h2>3.9.1</h2> <ul> <li>CLI: Fix ignored file has been cached incorrectly (<a href="https://redirect.github.com/prettier/prettier/pull/19483">#19483</a> by <a href="https://github.com/kovsu"><code>@kovsu</code></a>)</li> </ul> <p>🔗 <a href="https://github.com/prettier/prettier/blob/3.9.1/CHANGELOG.md#391">Changelog</a></p> <h2>3.9.0</h2> <p><a href="https://github.com/prettier/prettier/compare/3.8.5...3.9.0">diff</a></p> <p>🔗 <a href="https://prettier.io/blog/2026/06/27/3.9.0">Prettier 3.9: Major parser upgrades and Formatting improvements</a></p> <h2>3.8.5</h2> <ul> <li>Fix Flow variance annotation print (<a href="https://redirect.github.com/prettier/prettier/pull/19022">#19022</a> by <a href="https://github.com/marcoww6"><code>@marcoww6</code></a>)</li> </ul> <p>🔗 <a href="https://github.com/prettier/prettier/blob/3.8.5/CHANGELOG.md#385">Changelog</a></p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/prettier/prettier/blob/main/CHANGELOG.md">prettier's changelog</a>.</em></p> <blockquote> <h1>3.9.3</h1> <p><a href="https://github.com/prettier/prettier/compare/3.9.1...3.9.3">diff</a></p> <h4>Markdown: Fix unexpected removal of characters in liquid syntax (<a href="https://redirect.github.com/prettier/prettier/pull/19489">#19489</a> by <a href="https://github.com/seiyab"><code>@seiyab</code></a>)</h4> <!-- raw HTML omitted --> <pre lang="md"><code>// Input <!-- Input --> {{ page.title }} text <p><!-- Prettier 3.9.1 --><br /> {{ page.title<br /> text</p> <p><!-- Prettier 3.9.3 --><br /> {{ page.title<br /> }} text<br /> </code></pre></p> <h4>TypeScript: Allow decorators to be used with declare on class fields (<a href="https://redirect.github.com/prettier/prettier/pull/19492">#19492</a> by <a href="https://github.com/evoactivity"><code>@evoactivity</code></a>)</h4> <p>Extensively used within the Ember ecosystem, decorators with <code>declare</code> on class fields will ignore the babel parser error and allow Prettier to format the code without breaking it.</p> <!-- raw HTML omitted --> <pre lang="ts"><code>// Input export default class ProjectStatusComponent extends Component<ProjectStatusSig> { @service declare server: ServerService; } <p>// Prettier 3.9.1<br /> // SyntaxError: Decorators can't be used with a declare field. (2:3)<br /> // 1 | export default class ProjectStatusComponent extends Component<ProjectStatusSig> {<br /> //> 2 | <a href="https://github.com/service"><code>@service</code></a> declare server: ServerService;<br /> // | ^<br /> // 3 | }</p> <p>// Prettier 3.9.3<br /> export default class ProjectStatusComponent extends Component<ProjectStatusSig> {<br /> <a href="https://github.com/service"><code>@service</code></a> declare server: ServerService;<br /> }<br /> </code></pre></p> <h1>3.9.1</h1> <p><a href="https://github.com/prettier/prettier/compare/3.9.0...3.9.1">diff</a></p> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/prettier/prettier/commit/3732e1dee6a36bdb2e77a722d206a79ac7e67aa3"><code>3732e1d</code></a> Release 3.9.3</li> <li><a href="https://github.com/prettier/prettier/commit/a74a7b05dee7fbef39a6aeff378c3741e1a8ee15"><code>a74a7b0</code></a> Allow decorators to be used with <code>declare</code> on class fields (<a href="https://redirect.github.com/prettier/prettier/issues/19492">#19492</a>)</li> <li><a href="https://github.com/prettier/prettier/commit/bd9e11ab41e17a4f61f363a981c1ec24d2a4167a"><code>bd9e11a</code></a> Correct text identification in liquid syntax (<a href="https://redirect.github.com/prettier/prettier/issues/19489">#19489</a>)</li> <li><a href="https://github.com/prettier/prettier/commit/269eee3faa1f82b1de07bb7e4d15e1cee70f80d4"><code>269eee3</code></a> Bump Prettier dependency to 3.9.1</li> <li><a href="https://github.com/prettier/prettier/commit/ec7ccd1ea47c965bda3c958239899737e899603d"><code>ec7ccd1</code></a> Clean changelog_unreleased</li> <li><a href="https://github.com/prettier/prettier/commit/c47654c003fe525572e10d5cc1ea64d7b9c0ee55"><code>c47654c</code></a> Release 3.9.1</li> <li><a href="https://github.com/prettier/prettier/commit/06159aa254e662514d1c6f4de13fbac805984232"><code>06159aa</code></a> Fix bug in release script</li> <li><a href="https://github.com/prettier/prettier/commit/4bc5ab40582921f5283af4ff5d6511b58d25ec00"><code>4bc5ab4</code></a> Update file-entry-cache to 11.1.5 (<a href="https://redirect.github.com/prettier/prettier/issues/19483">#19483</a>)</li> <li><a href="https://github.com/prettier/prettier/commit/b7fd58bba027282038ad312af0522d4598e8b769"><code>b7fd58b</code></a> Release <code>@prettier/plugin-oxc@0.2.0</code> and <code>@prettier/plugin-hermes@0.2.0</code></li> <li><a href="https://github.com/prettier/prettier/commit/3006400fc2560e297b54d82c58cbc331ec87902c"><code>3006400</code></a> Revert changes in release script</li> <li>Additional commits viewable in <a href="https://github.com/prettier/prettier/compare/3.8.4...3.9.3">compare view</a></li> </ul> </details> <br /> Updates `typescript-eslint` from 8.61.1 to 8.62.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/typescript-eslint/typescript-eslint/releases">typescript-eslint's releases</a>.</em></p> <blockquote> <h2>v8.62.0</h2> <h2>8.62.0 (2026-06-22)</h2> <h3>🚀 Features</h3> <ul> <li>remove redundant package.json "files" (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12444">#12444</a>)</li> </ul> <h3>🩹 Fixes</h3> <ul> <li>add "files" to rule-schema-to-typescript-types (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12441">#12441</a>)</li> </ul> <h3>❤️ Thank You</h3> <ul> <li>Kirk Waiblinger <a href="https://github.com/kirkwaiblinger"><code>@kirkwaiblinger</code></a></li> </ul> <p>See <a href="https://github.com/typescript-eslint/typescript-eslint/releases/tag/v8.62.0">GitHub Releases</a> for more information.</p> <p>You can read about our <a href="https://typescript-eslint.io/users/versioning">versioning strategy</a> and <a href="https://typescript-eslint.io/users/releases">releases</a> on our website.</p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/typescript-eslint/CHANGELOG.md">typescript-eslint's changelog</a>.</em></p> <blockquote> <h2>8.62.0 (2026-06-22)</h2> <h3>🚀 Features</h3> <ul> <li>remove redundant package.json "files" (<a href="https://redirect.github.com/typescript-eslint/typescript-eslint/pull/12444">#12444</a>)</li> </ul> <h3>❤️ Thank You</h3> <ul> <li>Kirk Waiblinger <a href="https://github.com/kirkwaiblinger"><code>@kirkwaiblinger</code></a></li> </ul> <p>See <a href="https://github.com/typescript-eslint/typescript-eslint/releases/tag/v8.62.0">GitHub Releases</a> for more information.</p> <p>You can read about our <a href="https://typescript-eslint.io/users/versioning">versioning strategy</a> and <a href="https://typescript-eslint.io/users/releases">releases</a> on our website.</p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/typescript-eslint/typescript-eslint/commit/54e285728e5d8cb83fadb8041189f0c3b4ab436a"><code>54e2857</code></a> chore(release): publish 8.62.0</li> <li><a href="https://github.com/typescript-eslint/typescript-eslint/commit/81e4c2654c3f4d923766a888691add2c45b5d64a"><code>81e4c26</code></a> feat: remove redundant package.json "files" (<a href="https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/typescript-eslint/issues/12444">#12444</a>)</li> <li>See full diff in <a href="https://github.com/typescript-eslint/typescript-eslint/commits/v8.62.0/packages/typescript-eslint">compare view</a></li> </ul> </details> <br /> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Nikolay Vitkov <nvitkov@chromium.org> |
||
|
artboy
|
7fa95d3c33 |
fix: create PID directory with secure permissions (0o700) (#2262)
## Summary
- Add `mode: 0o700` to `fs.mkdirSync` when creating the PID directory
- Ensures the directory is always created with owner-only access
regardless of system umask
## Problem
The daemon creates the PID directory with `fs.mkdirSync(pidDir,
{recursive: true})` without specifying a mode. On systems with `umask
002`, the directory lands at mode 0775, which the daemon's own security
check rejects as "insecure permissions" and exits.
The daemon's test (`tests/daemon/symlink.test.ts`) already expects 0700
permissions, but nothing enforced it at runtime.
Fixes #2258
## Test Plan
- [ ] `umask 0002 && npx chrome-devtools-mcp@latest` no longer crashes
- [ ] `umask 0077 && npx chrome-devtools-mcp@latest` still works
- [ ] Existing daemon tests pass
|
||
|
Dominik Inführ
|
5d7b656050 |
feat: Add MCP tools for heap snapshot comparison (#2198)
This commit adds two MCP tools for comparing heap snapshots. `compare_heapsnapshot_summary` compares two memory snapshot and returns which classes have new/deleted objects. `compare_heapsnapshot_class_nodes` can then be used to list the object ids added and deleted for a specific class. Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> |
||
|
Piotr Paulski
|
e5bd334c97 |
chore: make TOON dependency optional (#2260)
Since toon dependency is only needed for `--experimentalToonFormat` flag, we can make it optional to decrease package size and security footprint for users that don't use it. Testing npx optional peer dependency resolution before the release: ``` npm i -g verdaccio verdaccio ``` On a separate terminal: ``` npm adduser --registry http://localhost:4873/ # follow prompts to create user and login # replace the published package in verdaccio npm unpublish chrome-devtools-mcp@1.4.0 --force --registry http://localhost:4873 npm publish --registry http://localhost:4873 # clear npx cache rm -rf ~/.npm/_npx # run the server from commandline and observe both packages being installed: npx --registry http://localhost:4873 --package chrome-devtools-mcp@latest --package @toon-format/toon chrome-devtools-mcp --experimentalToonFormat ``` Paste the following commands (each line separately) to manually interact with the mcp server and observe TOON formatted response directly ### 1. Initialize the session {"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test-client","version":"1.0.0"}}} ### 2. Confirm initialization {"jsonrpc":"2.0","method":"notifications/initialized"} ### 3. Navigate to Google (this will already create snapshot in most recent versions) {"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"navigate_page","arguments":{"url":"https://google.com"}}} ### 4. Take Snapshot (if not returned by the previous command) {"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"take_snapshot","arguments":{}}} --------- Co-authored-by: Piotr Paulski <piotrpaulski@chromium.org> |
||
|
Nikolay Vitkov
|
6a9466378c |
fix: respecte allow/block list in loadResouce (#2254)
Fixes https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/2218 Closes https://github.com/ChromeDevTools/chrome-devtools-mcp/pull/2225 |
||
|
Nikolay Vitkov
|
d1449654ac |
perf: use concurrent reads for loadIssueDescriptions (#2249)
💡 **What:** Refactored `loadIssueDescriptions` in `src/issue-descriptions.ts` to use `Promise.all` for reading all the `.md` description files concurrently rather than sequentially. 🎯 **Why:** Sequential file I/O operations create unnecessary blocking. The order in which files are read does not matter when populating a map, making it safe and more performant to read them concurrently. 📊 **Measured Improvement:** A local benchmark running against the 271 generated `.md` files in `build/src/third_party/issue-descriptions` showed a decrease from ~195ms (sequential) to ~56ms (concurrent), a >70% improvement. --- *PR created automatically by Jules for task [15785526133454041422](https://jules.google.com/task/15785526133454041422) started by @Lightning00Blade* --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> |
||
|
browser-automation-bot
|
0aaa8e3cc0 |
chore(main): release chrome-devtools-mcp 1.4.0 (#2228)
publish-on-tag / publish-to-npm (push) Has been cancelled
publish-on-tag / publish-to-mcp-registry (push) Has been cancelled
🤖 I have created a release *beep* *boop* --- ## [1.4.0](https://github.com/ChromeDevTools/chrome-devtools-mcp/compare/chrome-devtools-mcp-v1.3.0...chrome-devtools-mcp-v1.4.0) (2026-06-23) ### 🎉 Features * publish the skills folder ([#2229](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/2229)) ([ |
||
|
Alex Rudenko
|
e559765740 |
docs: update security.md (#2248)
Clarifies the MCP roots and network guardrails. |
||
|
Rayan Salhab
|
6225ffbaf1 |
fix: hide Windows update check consoles (#2231)
## Summary Fixes #2230. - Sets `windowsHide: true` on the detached update-check process so Windows does not flash a console window. - Also hides the `npm config get registry` subprocess used by the updater helper. - Covers the update-check spawn options in the existing tests. ## Verification - `NODE_OPTIONS=--max-old-space-size=4096 npm run build` - `npm run test:no-build -- tests/check-for-updates.test.ts` - `NODE_OPTIONS=--max-old-space-size=4096 npx eslint src/utils/check-for-updates.ts src/bin/check-latest-version.ts tests/check-for-updates.test.ts` - `npx prettier --check src/utils/check-for-updates.ts src/bin/check-latest-version.ts tests/check-for-updates.test.ts` - `git diff --check` Note: plain `npm run build` and full-repo `npm run check-format` hit the local Node heap limit in this runner; the same build passed with the heap limit raised, and touched-file lint/format checks passed. Co-authored-by: cyphercodes <cyphercodes@users.noreply.github.com> |
||
|
nyxst4ck
|
5a9d6af743 |
fix(network): keep redirect chain order consistent between text and JSON (#2221)
## Problem `get_network_request` returns, from the **same call**, both a human-readable text block (`toStringDetailed()`) and a `structuredContent.networkRequest` object (`toJSONDetailed()`) — emitted together in `McpResponse.ts`. For a request that went through HTTP redirects, the redirect chain comes out in **opposite orders** in the two representations: - `toJSONDetailed()` (`NetworkFormatter.ts`) reverses `redirectChain()` once → newest→oldest in the JSON. - the text formatter then reverses it **a second time** → oldest→newest in the text. Because each path calls `redirectChain()` separately and Puppeteer returns a fresh copy on every call (`HTTPRequest#redirectChain()` does `this._redirectChain.slice()`), the two reverses operate on different arrays and don't cancel. So a consumer reading the text and a consumer parsing the structured JSON from the same response see contradictory redirect orders. ## Solution Drop the redundant `.reverse()` in the text formatter so the rendered text uses the order already produced by `toJSONDetailed()`. Both representations are now consistent (newest→oldest), and `structuredContent` is unchanged. ## Why the existing tests didn't catch it - The existing "handles redirect chain" test uses a **single-element** chain, where reversing is a no-op. - `getMockRequest().redirectChain()` returned the **same array reference** on every call, unlike real Puppeteer — so the two reverses accidentally agreed in tests. This PR makes the mock return a fresh copy per call (matching Puppeteer) and adds a regression test with a multi-element chain that asserts the text and JSON orders match. ## Testing - `npm test` for the formatter suite passes. New test `renders the redirect chain in the same order in text and JSON` is **red** before the fix (text `[first, second]` vs JSON `[second, first]`) and **green** after, with no change to existing snapshots. - `npm run typecheck` and Prettier/ESLint are clean. No existing issue tracked this; found via code inspection and confirmed empirically. |
||
|
browser-automation-bot
|
4716a72017 |
chore(main): release chrome-devtools-mcp 1.3.0 (#2195)
publish-on-tag / publish-to-npm (push) Has been cancelled
publish-on-tag / publish-to-mcp-registry (push) Has been cancelled
🤖 I have created a release *beep* *boop* --- ## [1.3.0](https://github.com/ChromeDevTools/chrome-devtools-mcp/compare/chrome-devtools-mcp-v1.2.0...chrome-devtools-mcp-v1.3.0) (2026-06-18) ### 🎉 Features * Add get_heapsnapshot_dominators MCP tool ([#2215](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/2215)) ([ |
||
|
Nebrass Lamouchi
|
ba80096521 |
fix: handle screencast file extensions case-insensitively and clean up temp dir on failure (#2207)
Fixes #2206 ### Problem `screencast_start` matched the requested file extension with a **case-sensitive** `endsWith()` against `['.webm', '.mp4']` and **silently fell back to `.mp4`** when nothing matched. Combined with `ensureExtension()` (which replaces the extension), a request for `demo.WEBM` was recorded as **MP4** to **`demo.mp4`** — a different format *and* path than requested — and any unsupported extension (e.g. `recording.avi`) silently became `.mp4`. Separately, when `screencast_start` is called without a `filePath`, it creates a temp directory via `mkdtemp()`. If `page.screencast()` then throws (e.g. ffmpeg missing), that directory was leaked. ### Changes Two commits: 1. **`fix: match screencast extension case-insensitively and reject unsupported ones`** — match via `path.extname().toLowerCase()`; reject an explicitly requested but unsupported extension with an explicit error listing the supported formats; a missing extension still defaults to `.mp4`. 2. **`fix: clean up screencast temp directory when recording fails to start`** — remove the generated temp dir in the `catch` handler, but only when we own the generated path (never when the caller supplied `filePath`). | requested | before | after | | --------------- | --------------- | -------------- | | `demo.WEBM` | mp4 → `demo.mp4`| webm → `demo.webm` | | `recording.avi` | mp4 → `recording.mp4` | error (rejected) | | `demo.webm` | webm → `demo.webm` | unchanged | | *(no filePath)* | mp4 temp | unchanged | The matched extension is normalized to lower case (`demo.WEBM` → `demo.webm`). ### Testing Added three regression tests to `tests/tools/screencast.test.ts` using the existing `sinon`/`withMcpContext` harness. Verified locally against Chrome for Testing 149 (`PUPPETEER_EXECUTABLE_PATH`): - With the fix reverted, the two extension tests fail (uppercase `.WEBM` → mp4, `.avi` not rejected) and the cleanup test fails (temp dir left behind) — i.e. they fail for the right reason. - With the fix applied, the full `screencast.test.ts` suite passes (11/11). - `tsc --noEmit` and `npm run check-format` (eslint + prettier) are clean. > Note: I ran the `screencast` test file (which stubs `page.screencast`) plus typecheck/lint locally; the rest of the browser-based suite I left to CI. ### Notes for reviewers - I chose to **`throw`** for an unsupported explicit extension (consistent with the ffmpeg-missing `throw` in the same handler and with the issue's "reject with an explicit error"). Happy to switch to the softer `appendResponseLine(...) + return` style used by the in-progress guard if you'd prefer. - The two commits are independent and can be split if you'd rather take them separately. - I left the pre-existing `as \`${string}.webm\`` assertion on `resolvedPath` untouched to keep the diff focused, though it's slightly misleading now that the default is `.mp4`. --------- Co-authored-by: Nicholas Roscino <nroscino@google.com> |
||
|
Wolfgang Beyer
|
8fe398eb5d |
fix: handle missing third-party tool toolGroup description gracefully (#2224)
Angular's third-party tools currently do not provide a description of the toolGroup, only of the individual tools. We don't want to fail in this case. |
||
|
François Beaufort
|
163a581cc1 |
chore(webmcp): s/enable-features=WebMCPTesting/enable-features=WebMCP/g (#2223)
Following https://github.com/puppeteer/puppeteer/pull/15121, this PR updates WebMCP documentation and tests to switch to the blink feature WebMCP instead of WebMCPTesting which is removed in https://chromium-review.googlesource.com/c/chromium/src/+/7921035/comment/1f0982d8_fb3efb91/ |
||
|
Antoine Kingue
|
55c8a541d4 |
feat(screenshot): add CLI options to cap screenshot size at the source (#1823)
## Summary Adds **opt-in** CLI flags so operators can cap the size of screenshots returned by `take_screenshot` before they are embedded in the MCP response. Refs #879. The flags address two related symptoms reported when MCP clients display screenshots inline: 1. **Per-image dimension limit**: hosted LLM APIs commonly reject images exceeding per-image dimension constraints (typical caps are in the 2000-8000 px range, sometimes scaling down further when many images are in the same request). This is the exact error reported in #879. 2. **Cumulative request size**: after many captures, the cumulative base64 payload eventually pushes a request over the per-call body size limit imposed by the LLM API. Both can be mitigated at the source by reducing format/quality and downscaling the capture. ## New flags (all opt-in) - `--screenshot-format <jpeg|png|webp>`: override the default format used by `take_screenshot` when the caller does not specify one - `--screenshot-quality <0-100>`: override the default JPEG/WebP quality. Ignored for PNG - `--screenshot-max-width <px>`: downscale screenshots wider than this before they are returned - `--screenshot-max-height <px>`: downscale screenshots taller than this. Combines with `--screenshot-max-width`; the smaller scale wins so both bounds are respected while preserving aspect ratio For the exact error in #879, the recipe is `--screenshot-max-width=8000 --screenshot-max-height=8000` (or a smaller value such as `2000` if many images may end up in the same request, depending on the operator's chosen API). ## Implementation - Resizing leverages Puppeteer's `clip.scale` (CDP `Page.captureScreenshot`), so **no new dependencies**. - Source dimensions per capture mode: - viewport: `page.viewport()` - full page: `document.documentElement.scrollWidth/scrollHeight` via `page.evaluate()` - element (`uid`): `elementHandle.boundingBox()` - For element and full-page captures with a downscale clip, the call routes through `page.screenshot({clip})` so the scale parameter applies. `captureBeyondViewport` is left to Puppeteer's default (`true` when a clip is set), preserving correct behavior for elements below the fold and full-page captures. - ~150 lines of source code, ~200 lines of new tests. ## Backwards compatibility **Fully opt-in**: when no flags are set, `take_screenshot` returns the exact same bytes as before. No behavioral change for existing users. ## Design alignment - Aligned with the **"Reference over Value"** principle in `docs/design-principles.md`: the existing 2 MB threshold still routes oversized screenshots to a temporary file. This change only reduces the size of the **inline base64 fallback path**, which the principles document calls out as an acceptable exception when MCP clients display images natively. - The MCP server **hardcodes no LLM-specific size limits**. Operators pick the values that match their client/model combination. This keeps the maintenance surface here minimal as model limits evolve, and is intended as a **complement to, not a replacement for**, fixes in the MCP client itself. ## Addressing concerns raised in #879 > "It's not feasible for us to maintain this. Limits will change when models change." (@natorion) The flags are pure parameters; nothing about the upstream LLM is encoded in the server. When a vendor raises (or lowers) a limit, no code change is needed here, only the operator's CLI args change. > "`filePath` / `page_resize` already work as a workaround." (@OrKoN) `filePath` is great when the call site knows it's about to take a huge screenshot, but as you noted earlier in the thread, an oversized image already in the request history keeps causing failures even on subsequent calls. `page_resize` works but mutates the page being debugged. The resize in this PR happens **between Puppeteer and the MCP response**, so the inspected page is untouched and the failure mode is prevented at the source. > "Should be fixed client side." Agreed, this PR is intended as a complement, not a substitute. A client-side fix (e.g. compaction evicts/downsamples old images) handles the cumulative case for *any* MCP. A server-side cap handles the per-call dimension limit for users who hit it before compaction can kick in. The two address overlapping but distinct failure modes. Happy to drop or rework any of this if the maintainers prefer a different shape, for example making the threshold automatic from a single `--max-image-bytes` knob, or rejecting the PR entirely in favor of waiting for a client-side fix. Just wanted to put a concrete option on the table. ## Tests Added 6 new tests: - `honors screenshotFormat default from CLI args` - `keeps "png" as default format when no CLI override is set` - `downscales viewport screenshot when screenshotMaxWidth is set` - `downscales using the smaller scale when both max-width and max-height are set` - `does not resize when source is smaller than the max bounds` - `downscales full page screenshot when screenshotMaxWidth is set` All 627 tests in the suite pass. `npm run typecheck` and `npm run check-format` are clean. ## Notes for reviewers - The dimensions compared against `--screenshot-max-width/height` are **CSS pixels** (`page.viewport()`), not raw bitmap pixels. With `deviceScaleFactor > 1` (HiDPI emulation) the actual bitmap may still be larger. Happy to clarify this in the option description if preferred. - For element captures with a downscale clip, the call routes through `page.screenshot({clip})` instead of `element.screenshot()`. Same-frame elements are correct (boundingBox returns main-frame coords). I have **not** exercised this path against cross-origin iframe elements; let me know if you'd like a fallback there. - The PR is currently in **Draft** state pending CLA verification and any feedback on the framing above. Refs #879 Closes https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/879 |
||
|
Dominik Inführ
|
08c234ea4b |
feat: Add get_heapsnapshot_dominators MCP tool (#2215)
Adding the get_heapsnapshot_dominators MCP tool to show the dominators for a given node. In combination with get_heapsnapshot_retaining_paths this should help understand what keeps an object reachable and thus alive. Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> Co-authored-by: Nicholas Roscino <nroscino@google.com> |
||
|
bassem chagra
|
9e32002a69 |
fix: return error message when screencast_stop is called with no active recording (#2209)
## Summary
`screencast_stop` returns an empty response when no recording is active,
making it impossible for the calling agent to distinguish "stopped
successfully" from "nothing was recording."
`screencast_start` already handles its inverse case with an explicit
error (`"a screencast recording is already in progress"`), so this makes
`stop` consistent.
## Change
Added an error message when `screencast_stop` is called without an
active recording:
```ts
if (!data) {
response.appendResponseLine(
'Error: no active screencast recording to stop.',
);
return;
}
```
## Before
Empty tool response — agent cannot tell what happened.
## After
`Error: no active screencast recording to stop.`
---------
Co-authored-by: Nicholas Roscino <nroscino@google.com>
|
||
|
Wolfgang Beyer
|
ed02047ae9 |
fix: Reset toolGroups before gathering toolGroups (#2200)
`getToolGroups` can be called multiple times. We want to reset the `window.__dtmcp.toolGroups` array each time to prevent duplications. |
||
|
Dominik Inführ
|
4f8eb7ad6b |
feat: Add the get_heapsnapshot_edges MCP tool (#2180)
This PR adds the get_heapsnapshot_edges MCP tool. Agents can use it to look at the outgoing edges for a specifc object. Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> |
||
|
Dominik Inführ
|
6bd8c91678 |
feat: Use HeapSnapshotProxy.nodeIndexById (#2193)
Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> |
||
|
Serhii Zghama
|
b646feb4f3 |
feat: include page title in list_pages output (#2166)
## Motivation `list_pages` shows each page's URL but not its title, which is painful when multiple pages share a host — e.g. several tabs under `app.example.com/u/0/`, `/u/1/`, `/u/2/`. There's no way to tell which is which without visiting each one, even though every page has a usable `document.title`. Fixes #2156. Closes #2175 ## What this changes - `list_pages` text output now shows the title before the URL when available: `1: My Page (https://example.com) [selected]`. If the page has no title (e.g. `about:blank`), the format is unchanged. - The structured content entry for each page now includes a `title` field alongside `id`, `url`, and `selected`. - `page.title()` is awaited with a `.catch(() => '')` so a closed or erroring page silently falls back to the URL-only format. - `format()` is made `async` to support the `await` inside the page loop; `createStructuredPage()` likewise becomes `async`. ## Testing Start the MCP server with multiple tabs open. Call `list_pages` — pages with titles now display as `id: Title (url)`. Pages without titles (`about:blank`, data URLs) display as before. --------- Co-authored-by: Piotr Paulski <31672205+zyzyzyryxy@users.noreply.github.com> |
||
|
Nikolay Vitkov
|
834b259eb2 |
chore: expose loadResouce HostBinding (#2194)
This makes sure that if any resource that is loaded via the HostBinding will be correctly checked agains the roots object. |
||
|
Dominik Inführ
|
a97c642d43 |
feat: Add retaining paths MCP tool (#2187)
This PR adds the `get_heapsnapshot_retaining_paths` MCP tool. This can be used to find the paths from the target object to the GC roots which keep that object alive. Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> |
||
|
Nikolay Vitkov
|
bede4fbdfa |
chore: install HostBindingAdapter (#2186)
This PR introduces the HostBindingAdapter to utilize the functions usually available to DevTools. Additionally I moved all the DevTools related files under a `devtools` directory to better separate the extractor logic. The patch scripts for DevTools were moved under a function to remove the side-effect nature of the file. Now gets called in a the creation of the McpContext (and a before hook in test.) |
||
|
browser-automation-bot
|
702d3734f2 |
chore(main): release chrome-devtools-mcp 1.2.0 (#2153)
publish-on-tag / publish-to-npm (push) Has been cancelled
publish-on-tag / publish-to-mcp-registry (push) Has been cancelled
🤖 I have created a release *beep* *boop* --- ## [1.2.0](https://github.com/ChromeDevTools/chrome-devtools-mcp/compare/chrome-devtools-mcp-v1.1.1...chrome-devtools-mcp-v1.2.0) (2026-06-08) ### 🎉 Features * add experimental TOON support for structured content output ([#2042](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/2042)) ([ |
||
|
Piotr Paulski
|
aa33bff19f |
feat: add experimental TOON support for structured content output (#2042)
Adds `--experimentalToonFormat` boolean flag, controlling how structured content is formatted in text response. By default, custom shorthand format is used. With this flag, TOON format (see https://github.com/toon-format/toon) is used instead. TOON format is supposed to be more token-efficient and less error-prone for agents to understand than json, but it's not clear if it will be better on those metrics than the custom format used so far. (Evals pending) One clear benefit over custom format would be less code to maintain if we decide to fully switch to TOON, due to dropping custom formatters and reusing json formatters used for structuredContent anyways. Co-authored-by: Piotr Paulski <piotrpaulski@chromium.org> |
||
|
Nicholas Roscino
|
29e389848f |
feat: implement extension service worker logs (#1915)
This PR introduces the possiblity to collect console messages from service workers. |
||
|
Natasha Gorshunova
|
02b4492ca6 |
feat: support allowedUrlPattern & blockedUrlPattern Options (#2037)
## Support for Network Blocklists and Allowlists (`--blocked-url-pattern` & `--allowed-url-pattern` arguments) This PR adds support for CLI options to restrict network access in the browser session via URL patterns. ### Key Features & How It Works - **Pattern Matching:** Utilizes the [URLPattern Standard](https://urlpattern.spec.whatwg.org/) for pattern matching. - **Target Detachment:** Silently detaches from targets (pages/tabs) whose URLs match blocked patterns (or do not match allowed patterns) upon connection. - **Runtime Blocking:** Prevents navigations and blocks runtime requests (such as fetch/XHR and subresources) if they violate the pattern rules. - **Mutual Exclusivity:** `--blocked-url-pattern` and `--allowed-url-pattern` conflict with each other and cannot be configured simultaneously. - **Browser Requirements:** - **`--allowed-url-pattern`**: Requires **Chrome 149+**. - **`--blocked-url-pattern`**: Works on Chrome versions older than 149, but **Chrome 149+ is highly recommended**. ### Important Limitations & Side Effects - **Network Emulation/Throttling Conflict:** Network throttling is disabled when a network blocklist/allowlist is configured, to avoid conflicting with Puppeteer's underlying blocking mechanisms. - Using the `emulate` tool to modify `networkConditions` (e.g. setting to `Offline`) will throw an error: *`Network throttling is not supported when network blocking (allowlist/blocklist) is configured.`* - Other emulation settings (e.g., `cpuThrottlingRate`, `geolocation`, `viewport`) are unaffected and remain fully functional. --- ### Configuration Examples #### 1. Blocking specific domains or endpoints (Blocklist) Add the `--blocked-url-pattern` options to the `args` list in your MCP settings file: ```json { "mcpServers": { "chrome-devtools": { "command": "npx", "args": [ "chrome-devtools-mcp@latest", "--blocked-url-pattern=*://*.blocked-example.com/*", "--blocked-url-pattern=*://*.another-blocked-example.com/*" ] } } } ``` #### 2. Restricting access to authorized domains (Allowlist) Add the `--allowed-url-pattern` options to restrict the browser to permitted hosts (requires Chrome 149+): ```json { "mcpServers": { "chrome-devtools": { "command": "npx", "args": [ "chrome-devtools-mcp@latest", "--allowed-url-pattern=https://*.allowed-example.com/*", "--allowed-url-pattern=https://*.another-allowed-example.com/*" ] } } } ``` --------- Co-authored-by: Natallia Harshunova <nharshunova@chromium.org> Co-authored-by: Alex Rudenko <alexrudenko@chromium.org> |
||
|
Nikolay Vitkov
|
f90f863d4b |
perf: lighthouse file saves to run concurrently (#2178)
💡 **What:** The optimization implemented is refactoring the sequential file save loops for Lighthouse audits in `src/tools/lighthouse.ts` to utilize concurrent execution via `Promise.allSettled`. 🎯 **Why:** Previously, the tool saved generated lighthouse reports linearly (e.g. `html` then `json`), causing unnecessary synchronous blocking on I/O operations (`fs.writeFile` under the hood via `context.saveFile`). 📊 **Measured Improvement:** In a benchmark designed to simulate I/O constraint simulating a 250ms delay for each file write (`tests/performance/lighthouse_save.bench.ts`), the optimization reduced file save time from 2749.58ms to 2460.11ms, showing the I/O times were successfully overlapped and providing a ~250ms gain. --- *PR created automatically by Jules for task [9309630185581322418](https://jules.google.com/task/9309630185581322418) started by @Lightning00Blade* --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> |
||
|
Nikolay Vitkov
|
0217397257 |
feat: memory debugging tools (#2169)
Updates the flag for the memory tooling to remove the experimental bit (keep alias for backwards compatibility). And updates the SKILLs to reflected the update names and point to the available tools. Q: Should it be called `take_heapsnapshot` or `take_heap_snapshot`? |
||
|
Dominik Inführ
|
8713b93b41 |
feat: Adds close_heapsnapshot MCP tool (#2174)
This commit adds the close_heapsnapshot MCP tool such that the coding agent can close heap snapshots again. Co-authored-by: Dominik Inführ <dinfuehr@chromium.org> Co-authored-by: Nicholas Roscino <nroscino@google.com> |
||
|
Wolfgang Beyer
|
30d59a7872 |
feat: Handle multiple providers of third-party developer tools (#2168)
This allows a page to have multiple providers of third-party developer tools, which each respond to the `devtoolstooldiscovery` event. - Multiple `ToolGroup`s - MCP tool responses only mention third-party developer tools, if there are any. Otherwise this part of the output is skipped. |
||
|
Nikolay Vitkov
|
bf0574da8c |
refactor: change type of logger (#2165)
This change aligns most of our logger allowing them to be omitted when needed meaning code inside the args will not be executed unconditionally - example `logger?.(JSON.stringy(X))`. Currently only changes the type, while in a follow up I will remove the `debug` package and update the file logs. |
||
|
Nikolay Vitkov
|
2e039c09e1 |
refactor: use validate files on the tool level (#2152)
Fixes https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/2138 Closes #2150 |
||
|
Nicholas Roscino
|
b39131172b |
chore: reflect emulated device in CrUX data (#2131)
CrUX data returned with the performance tool now reflects the emulated device Closes: #1813 |
||
|
dependabot[bot]
|
7b5ec3a1b8 |
chore(deps-dev): bump chrome-devtools-frontend from 1.0.1632065 to 1.0.1635648 in the bundled-devtools group (#2129)
Bumps the bundled-devtools group with 1 update: [chrome-devtools-frontend](https://github.com/ChromeDevTools/devtools-frontend). Updates `chrome-devtools-frontend` from 1.0.1632065 to 1.0.1635648 <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/baad1f9760c7168078a7734315493801271aa34e"><code>baad1f9</code></a> Roll browser-protocol and CfT</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/44d52116dc42f14036103e26f04e4a0e3fa443b4"><code>44d5211</code></a> Network: ensure too large images are linked</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/b8fec712b8d2c9bbaee7672dfda2d89170ea7c2b"><code>b8fec71</code></a> Update DevTools DEPS (trusted)</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/7de281862ab9b80aa6fa27c00e939b79a3022b62"><code>7de2818</code></a> Roll browser-protocol and CfT</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/1adef13b6f26cc7be5e3f771c1b66339c3fad03f"><code>1adef13</code></a> Update DevTools DEPS (trusted)</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/839f6d242ac83a8c265ebaaf48e8e0c6f92d5925"><code>839f6d2</code></a> Update DevTools DEPS (trusted)</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/8bbc3ffedbe713e5dba10f48552413f4af1ea624"><code>8bbc3ff</code></a> Update DevTools DEPS (trusted)</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/f4d0583fc171242e6e5c1e408e1d18da7a2c413d"><code>f4d0583</code></a> Add Plus Button (2/3): declarative plus-button option for TabbedLocation</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/f8fbed4db685c65f13af56dcad96531b44b9a4b7"><code>f8fbed4</code></a> AI: Fix cross-origin data leak in AccessibilityAgent</li> <li><a href="https://github.com/ChromeDevTools/devtools-frontend/commit/9be84a9904de7d976f4713aafc28cd1edc9ad465"><code>9be84a9</code></a> Updated performance formatters to support an optional deviceScope,</li> <li>Additional commits viewable in <a href="https://github.com/ChromeDevTools/devtools-frontend/compare/v1.0.1632065...v1.0.1635648">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore <dependency name> major version` will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself) - `@dependabot ignore <dependency name> minor version` will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself) - `@dependabot ignore <dependency name>` will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself) - `@dependabot unignore <dependency name>` will remove all of the ignore conditions of the specified dependency - `@dependabot unignore <dependency name> <ignore condition>` will remove the ignore condition of the specified dependency and ignore conditions </details> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Nicholas Roscino <nroscino@google.com> |
||
|
browser-automation-bot
|
3ba70d350a |
chore(main): release chrome-devtools-mcp 1.1.1 (#2148)
publish-on-tag / publish-to-npm (push) Has been cancelled
publish-on-tag / publish-to-mcp-registry (push) Has been cancelled
🤖 I have created a release *beep* *boop*
---
##
[1.1.1](https://github.com/ChromeDevTools/chrome-devtools-mcp/compare/chrome-devtools-mcp-v1.1.0...chrome-devtools-mcp-v1.1.1)
(2026-05-27)
### 🛠️ Fixes
* **cli:** have pageId as first argument
([#2142](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/2142))
([
|
||
|
Samiya Caur
|
60be3e6bc1 |
fix(cli): have pageId as first argument (#2142)
Refs #1777 This change makes pageId as the first argument for CLI if experimentalPageIdRouting flag is enabled Co-authored-by: Samiya Caur <samiyac@chromium.org> |
||
|
browser-automation-bot
|
0089ebdd37 |
chore(main): release chrome-devtools-mcp 1.1.0 (#2086)
publish-on-tag / publish-to-npm (push) Has been cancelled
publish-on-tag / publish-to-mcp-registry (push) Has been cancelled
🤖 I have created a release *beep* *boop* --- ## [1.1.0](https://github.com/ChromeDevTools/chrome-devtools-mcp/compare/chrome-devtools-mcp-v1.0.1...chrome-devtools-mcp-v1.1.0) (2026-05-26) ### 🎉 Features * add extraHttpHeaders emulation to emulate tool ([#1176](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/1176)) ([ |
||
|
Wolfgang Beyer
|
0c3ac378a9 |
fix: Set viewport after updating timeouts when setting emulation (#2134)
Tentatively addresses #2115 |
||
|
Alex Rudenko
|
521c388624 |
refactor: remove redundant validatePath calls (#2136)
We should primarily validate in the tool calls before we start invoking tool handlers. |
||
|
Diego Ballesteros Villamizar
|
43b934cd98 |
fix: exit on stdin EOF and SIGTERM/SIGINT/SIGHUP, closing the browser cleanly (#2117)
Fixes #2116. `chrome-devtools-mcp-main.ts` currently has no shutdown handler. After a session calls `navigate_page` (or anything else that launches Chrome), the Chrome subprocess keeps the Node event loop ref'd, so closing stdin (the stdio MCP convention for "I'm done") doesn't make the server exit. Callers that close stdin to terminate the server have to fall back to SIGTERM / SIGKILL on every page-loaded session — deterministically, not flakily. This change: 1. Adds `closeBrowser()` in `browser.ts` that calls `browser.close()` for launched instances (reaps the Chrome subprocess) and `browser.disconnect()` for attached instances (leaves the user's Chrome alive). No-op if no browser is active or the connection has already been dropped. 2. Registers shutdown handlers in `chrome-devtools-mcp-main.ts` for: - `stdin.on('end' | 'close')` — stdio MCP transport convention - `SIGTERM` / `SIGINT` / `SIGHUP` — clients that signal instead of closing stdin (`SIGHUP` for parity with `src/daemon/daemon.ts`) The handler is idempotent (guarded `shuttingDown` flag), and has an unref'd 10s timeout backstop in case Chrome teardown hangs (slow `beforeunload` handlers, many tabs, etc.). ### Note on scope This complements (does not replace) the client-side fixes filed against #1765, e.g. google-gemini/gemini-cli#13391 and anthropics/claude-code#42300. The MCP stdio convention is that closing stdin signals shutdown; a server that doesn't honor that forces every client to special-case it. The watchdog sub-process (`src/telemetry/watchdog/main.ts:145-146`) and the daemon (`src/daemon/daemon.ts:224-230`) both already implement this for the same reason — this PR extends the same pattern to the main entry point so all three execution paths behave consistently. ### Measurement Repro script in #2116, same env (chrome-devtools-mcp@1.0.1, Chrome 148.0.7778.178, Node v24.11.1, Linux), 10 iterations: | Scenario | Before | After | |---|---|---| | `tools/list only` (no navigation) | 10/10 clean, 30-37 ms | 10/10 clean, 29-40 ms | | `navigate example.com` | 10/10 SIGTERM at ~5080 ms | 10/10 clean at 145-180 ms | ### Notes - I didn't add a subprocess-based test for this; the existing `tests/utils.ts:runCli` infrastructure targets the `chrome-devtools` CLI, not the stdio MCP server, and a shutdown-timing test would introduce non-trivial Chrome-startup flakiness in CI. Happy to add one if maintainers want it — pointer to the right test directory appreciated. |
||
|
Alex Rudenko
|
176eb69513 | fix: use realpath for MCP roots validation (#2127) | ||
|
Nicholas Roscino
|
2eab509380 | chore: fixed typo from longtitude to longitude (#2132) |