This adds a `list_in_page_tools` MCP tool. When called, it dispatches a
`devtoolstooldiscovery` event on the active page. The page announces its
exposing tools by calling the event's `respondWith` method, which causes
the exposed tools to be stashed on the page's `window` object. This list
of in-page tools is then appended to the `list_in_page_tools` response.
Calling the exposed in-page tools from the MCP server will be handled in
a follow-up.
## Problem
After closing the currently selected page, calling `list_pages` throws
an error:
```
The selected page has been closed. Call list_pages to see open pages.
```
This creates a deadlock: the error message tells users to call
`list_pages`, but `list_pages` itself throws the same error.
## Root Cause
`list_pages` is defined with `definePageTool`, which marks it as
`pageScoped: true`. The handler dispatch in `index.ts` (line ~186) calls
`context.getSelectedMcpPage()` for all page-scoped tools **before**
invoking the handler. When the selected page is closed,
`getSelectedPptrPage()` throws.
However, `list_pages` doesn't actually use the `page` parameter — its
handler only calls `response.setIncludePages(true)`.
## Fix
Change `list_pages` from `definePageTool` to `defineTool`. This bypasses
the page-scoped check while preserving all existing behavior since the
handler never used the page reference.
## Testing
Reproduced the issue following the steps in #1138:
1. Call `list_pages` → returns page list ✅
2. Close the selected page
3. Call `list_pages` → now returns updated page list instead of throwing
✅Fixes#1138
---------
Co-authored-by: Piotr Paulski <piotrpaulski@chromium.org>
The changes in the PR intercepts the name of the MCP client right after
server initialization, coverts it into one of the existing enum values,
and append it with the telemetry request.
Note that the client name is unset if there is no client connected yet.
This means the server_start event won't have a client name.
Tested with gemini-cli.
---------
Co-authored-by: Yulun Zeng <yulunz@chromium.org>
This should reduce the flakiness and issue with finding open DevTools
tabs for the corresponding pages.
Currently we do multiple loops over all the targets, so this should have
a nice performance improvement when multiple pages are opened.
With a fallback for older versions.
Issue #1192
## Problem
In `--autoConnect` mode, `chrome-devtools-mcp` experiences a severe
memory leak (~13 MB/min) when Chrome is actively used. This eventually
leads to OOM crashes or kernel panics.
The root cause is in `src/PageCollector.ts`:
1. `NetworkCollector` overrides `splitAfterNavigation` but forgets to
call `navigations.splice(this.#maxNavigationSaved)`, causing the array
of navigations to grow infinitely.
2. Even within a single navigation (e.g., in long-lived SPA
applications), the `navigations[0]` array grows infinitely because there
is no limit on the number of items collected per navigation. Since
`HTTPRequest` objects are heavy, this quickly exhausts memory.
## Solution
1. Changed `#maxNavigationSaved` to `protected maxNavigationSaved` so
subclasses can access it.
2. Added `navigations.splice(this.maxNavigationSaved)` to
`NetworkCollector.splitAfterNavigation` to ensure old navigations are
properly discarded.
3. Introduced `protected maxItemsPerNavigation = 5000` to limit the
number of items stored per navigation. When the limit is reached, the
oldest item is removed (`shift()`), preventing unbounded memory growth
in SPAs.
Tested locally by running `npm run build` and verifying the fix.
---------
Co-authored-by: Wolfgang Beyer <woolfi.b@gmail.com>
This should reduce the flakiness and issue with finding open DevTools
tabs for the corresponding pages.
Currently we do multiple loops over all the targets, so this should have
a nice performance improvement when multiple pages are opened.
- `chrome-devtools-mcp.js` is the `npx chrome-devtools-mcp`
- `chrome-devtools.js` is the new CLI
- `-cli-options.js` is the corresponding options
- all these files are in the bin folder to indicate they are executable
This PR implements the ability to trigger an extension action by passing
it an extension id.
It uses puppeteer internals and the canary chrome version in tests since
the TriggerAction CDP command is still not available in the current
stable release.
- reduces the token usage.
- makes emulation and script compatible with CLI.
- documents .nullable() and .object() restrictions for the future.
- the emulation tools do not have nullable anymore and undefined would
clear the emulation instead. The model is thus required to provide all
emulation settings at once.
Closes https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/918
- renamed getSelectedPage to getSelectedPptrPage
- removes getSelectedPptrPage from tool interfaces
- moves dialog handling to McpPage
- makes responses to be optionally McpPage-scoped
The client is meant to start the daemon if it is not running or connect
to the existing one. Long-running client connections are not needed yet.
Removed previous direct daemon test as we better test it via the client,
the intended way to manage the daemon.
## Summary
Adds optional `pageId` routing to page-scoped tools, gated behind
`--experimental-page-id-routing`. When enabled, multi-agent callers can
target a specific page without relying on global selection state. Fully
backward-compatible: without the flag, behavior is unchanged.
### Key changes
- **`pageScoped` annotation**: tools declare `pageScoped: true`; the
server merges `pageId` into their schema at registration time (when the
flag is on)
- **`McpPage` wrapper**: consolidates per-page state (numeric id,
isolated context name, focus tracking) into a single class
- **Request-scoped page routing**: `resolvePageById()` resolves the
target page, `setRequestPage()` threads it through the handler so tools
like `getSelectedPage()` see the right page
- **`assertPageIsFocused`**: keyboard/input tools validate that the
target page holds browser focus, returning an actionable error ("call
select_page first") instead of silently dispatching to the wrong page
- **`--experimental-page-id-routing` CLI flag** (hidden): gates schema
injection and request-scoped routing so the feature can be tested before
graduating
- **Eval scenarios**: `page_id_routing_test` and
`page_focus_keyboard_test` with `serverArgs` support in the eval harness
Addresses #1019
Implements a daemon process needed for the CLI. The daemon has commands
to start/stop itself as well as an ability to forward data to the
managed MCP server. Local sockets or named pipes are used depending on
the platform.
The .sock and .pid files are placed under
XDG_RUNTIME_DIR/chrome-devtools-mcp or /tmp/chrome-devtools-mcp for
short socket paths.
It uses Puppeteer's PipeTransport to avoid re-implementing \0 terminated
messages.
Note the code is not used anywhere at the moment.
`type_text` is useful for pages that do not have a11y and, thus, uid is
not known. It's also useful for testing user-like keyboard input and
testing the focus state changes. The `fill` tools force the focus change
and require an uid and therefore are not suitable for these tasks.
## Summary
Enhances wait_for to support waiting on multiple possible texts and
resolve when any one appears.
This addresses long-running flows that can end in different UI outcomes
(for example, "Complete" or "Error"), avoiding unnecessary 300s waits
when only one expected string is provided.
Closes#916.
## Tool Update
### wait_for
Waits for text on the selected page, now with any-match support.
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| text | string \| string[] | yes | A single text or a non-empty list of
texts. Resolves when any value appears. |
| timeout | integer | no | Maximum wait in ms (0 keeps default
behavior). |
---
## Design / Implementation
- Kept backward compatibility: existing single-string text calls
continue to work unchanged.
- Added schema support for string | string[] with non-empty array
validation.
- Updated context API to accept string | string[].
- Matching logic now normalizes to an array and races all candidates
across all frames using both:
- aria/<text>
- text/<text>
- Added clearer response output for array input:
- Element matching one of ["Complete","Error"] found.
- Updated generated tool docs for the new wait_for contract.
- Improved docs generation to render ZodUnion types (so union params are
documented correctly, not as unknown).
---
## Tests
Added/updated coverage for:
- Schema acceptance of:
- single string
- non-empty string array
- rejection of empty array
- Any-match array success case
- Any-match array when matching text appears later (async/delayed
content)
- Existing wait_for behavior remains covered for single-text usage
Executed relevant test suites:
- tests/tools/snapshot.test.ts
- tests/McpContext.test.ts
- tests/index.test.ts
Confirmation after the change applied:
https://opncd.ai/share/8m6I4r4a
Wolfgang Beyer