## 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
## Summary
Adds storage-isolated browser contexts via an optional `isolatedContext`
parameter on the `new_page` tool, following the simplified design
proposed by @OrKoN in #926.
Pages created with the same `isolatedContext` name share cookies,
localStorage, and storage. Pages in different isolated contexts (or the
default context) are fully isolated — ideal for testing multi-user
real-time features like chat, notifications, or collaborative editing.
## Changes
### `new_page` tool
- New optional `isolatedContext: string` parameter
- If specified, creates/reuses a named `BrowserContext` and opens a page
in it
- If omitted, uses the default browser context (existing behavior
unchanged)
### `McpContext`
- `#isolatedContexts` Map: LLM-provided names → Puppeteer
`BrowserContext` instances
- `#pageToIsolatedContextName` WeakMap: GC-safe page → context name
reverse lookup
- Auto-discovery: externally created browser contexts get
`isolated-context-1`, `isolated-context-2`, etc.
- `getIsolatedContextName(page)`: returns the isolated context name for
a page (used by response formatting)
- `page.browserContext()` used for context membership detection (no
custom target event forwarding needed)
- No context cleanup in `dispose()` or `closePage()` — either the entire
browser is closed or we disconnect without destroying state
### `McpResponse`
- Page list includes `isolatedContext=${name}` labels (both text and
structured JSON output)
### `ToolDefinition`
- `Context` interface extended with `getIsolatedContextName(page)`
method
## What's NOT included (by design)
- **No `TargetEventEmitter`**: Puppeteer forwards target events from
`BrowserContext` → `Browser` internally
- **No context cleanup**: Browser contexts are not closed on `dispose()`
or page close, per maintainer guidance
- **No `about:blank` cleanup**: Default context and isolated contexts
coexist side-by-side
## Example
```
> new_page url="https://app.example.com/chat" isolatedContext="userA"
> new_page url="https://app.example.com/chat" isolatedContext="userB"
> list_pages
Page 1: [app.example.com/chat] isolatedContext=userA
Page 2: [app.example.com/chat] isolatedContext=userB [selected]
```
Pages in different isolated contexts have fully independent cookies,
localStorage, IndexedDB, and WebSocket connections.
## Tests
- 6 new tests covering `isolatedContext` feature in
`tests/tools/pages.test.ts`
- All existing tests pass (333+)
- Zero type errors, lint clean
Closes#926
---------
Co-authored-by: Alex Rudenko <alexrudenko@chromium.org>
## Summary
Adds `screencast_start` and `screencast_stop` MCP tools that allow
agents to record a video of a page using Puppeteer's `page.screencast()`
API.
Only enabled if the command line option `--experimental-screencast` is
provided
Closes#878.
## New Tools
### `screencast_start`
Starts recording a screencast (video) of the selected page in mp4
format.
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `path` | string (optional) | temp file | Output file path |
### `screencast_stop`
Stops the active recording and reports the saved file path.
## Design
- **Start/stop pair** following the `performance_start_trace` /
`performance_stop_trace` pattern
- **State management** via `getScreenRecorder()` / `setScreenRecorder()`
on the Context interface
- **Category**: `DEBUGGING` (alongside `take_screenshot`)
- **ffmpeg dependency**: Clear error message when ffmpeg is not
installed
- **Temp file fallback**: When no `path` is provided, creates a temp
file with the correct extension
---------
Co-authored-by: Alex Rudenko <alexrudenko@chromium.org>
LLM are trained to know the common status code so we can rely on that
when displaying the status code and fall back to text in case of errors
or pending reponse.
This PR wires up the default DevTools ignore listing to hide frames from
third party scripts in stack traces. By default, we ignore:
* Scripts with `/node_modules/` in their URL or where the URL starts
with `node:/`
* Scripts that are marked as ignore listed in the source map
* Content scripts from extensions
The PR adds both, unit tests and an e2e test. This is because we allow
the unit test to pass a mocked ignore checker, where-as the e2e uses the
real DevTools one.
This PR refactors the stack trace formatting logic a bit: We split the
`formatStackTrace` function into 2: One for the top-level stack trace
and the rest for the recursive ones. We also return lines separately so
we can slice the result later.
This PR implements formatting for `SymbolizedError` objects that are
part of "resolved arguments". A follow-up PR will handle the actual
conversion of `Error` remote objects to `SymbolizedError`s.
This PR shuffles code around in `ConsoleFormatter` so the data flow is
more clear and flexible. Instead of augmenting an existing instance via
`#loadDetailedData` we pass the detailed data (if needed) via
constructor. The overall public API stays exactly the same, only the
internal implementation changed.
This also makes it trivial to inject "resolved arguments for testing",
which we'll need to test `SymbolizedError` instances as part of
`resolvedArgs`.
Drive-by: Make options and message ID mandatory. All call-sites already
passed these so its a no-op to tighten the type here and we can simplify
toString() a bit.
The "SymbolizedError" class represents a fully resolved error: The stack
trace is fully resolved and (in the future), the full `Error.cause`
chain is also fully resolved.
We'll use the `SymbolizedError` for both "uncaught exceptions" as well
as when logging `Error` objects to the console (e.g. `console.log(new
Error())`. This means the `resolvedArgs` array in `ConsoleFormatter`
will contain one `SymbolizedError` instance for every `Error` object
logged.
We upgrade the performance trace tools to include real-user experience
data from the Chrome User Experience Report (CrUX).
https://developer.chrome.com/docs/cruxhttps://developer.chrome.com/docs/crux/methodology
### Deets
* When a trace is stopped, the server now extracts the primary
navigation URLs from the trace (determined by insightSets).
* It calls the public CrUX API to fetch field metrics (LCP, INP, CLS)
for each unique URL/Origin.
* The formatting of crux data is handled by upstream TraceFormatter, but
it looks like this:
```md
Metrics (field / real users):
- LCP: 2595 ms (scope: url)
- LCP breakdown:
- TTFB: 1273 ms (scope: url)
- Load delay: 86 ms (scope: url)
- Load duration: 451 ms (scope: url)
- Render delay: 786 ms (scope: url)
- INP: 140 ms (scope: url)
- CLS: 0.06 (scope: url)
- The above data is from CrUX–Chrome User Experience Report. It's how the page performs for real users.
- The values shown above are the p75 measure of all real Chrome users
- The scope indicates if the data came from the entire origin, or a specific url
- Lab metrics describe how this specific page load performed, while field metrics are an aggregation of results from real-world users. Best practice is to prioritize metrics that are bad in field data. Lab metrics may be better or worse than fields metrics depending on the developer's machine, network, or the actions performed while tracing.
```
**Privacy Considerations:**
* Updates the server README to inform users that performance analysis tools may send trace URLs to the Google CrUX API.
* Adds a notification message to the server startup logs regarding the CrUX API interaction.
Doc: go/crux-in-bifrost
Fixes b/446630695
---------
Co-authored-by: Alex Rudenko <alexrudenko@chromium.org>
Co-authored-by: Alex Rudenko <OrKoN@users.noreply.github.com>
Note that we replace the existing "pageerror" handler with our new
`UncaughtError` handler. The latter has a structured stack trace
attached which we can source map via DevTools.
This regresses the current functionality slightly, as we lose
"pageerror"s for workers and oopif.
Alex Rudenko