This PR introduces a feature to disable some of the MCP server tool
categories to tailor it to specific use cases.
For example,
```
npx chrome-devtools-mcp@latest --no-category-emulation Disable tools in the emulation category
npx chrome-devtools-mcp@latest --no-category-performance Disable tools in the performance category
npx chrome-devtools-mcp@latest --no-category-network Disable tools in the network category
```
I checked Puppeteer implementation and it computes the text based on all
args so we should treat the first arg in a special way. Also, changes
the format to print count of args in the list and full args in the
details only.
Locally the test `with full page resulting in a large screenshot` would
fail semi consistently.
With what I think is just things not getting loaded fully, so scroll to
the bottom to fix that.
## Summary
Add support for connecting to Chrome via WebSocket endpoint with custom
headers, enabling authenticated remote debugging scenarios and providing
an alternative to the HTTP-based connection method.
## What's New
This PR introduces two new CLI arguments:
- **`--wsEndpoint` / `-w`**: Connect directly to Chrome using a
WebSocket URL
- Example: `ws://127.0.0.1:9222/devtools/browser/<id>`
- Alternative to `--browserUrl` (mutually exclusive)
- **`--wsHeaders`**: Pass custom headers for WebSocket connections (JSON
format)
- Example: `'{"Authorization":"Bearer token"}'`
- Only works with `--wsEndpoint`
## Use Cases
- **Authenticated remote debugging**: Use API keys, tokens, or custom
auth headers
- **Secured instances**: Connect to browser instances requiring
authentication
Fixes a bug where the output contained "this is a high level summary"
before then outputting the call frame / network format information
before then outputting the trace summary.
With this commit, we now output the summary & insights before ending
with the format information.
https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/320
Issue:
It would be very useful to have the ability to simulate offline network
conditions directly through the MCP emulate_network command, similar to
how it's possible in DevTools.
Currently, the command doesn’t support an Offline state, which limits
testing for PWA and offline-first web applications. Adding this option
would make it easier to automate and validate offline behavior through
MCP scripts or tools that rely on this API.
Solution
- Add 'Offline' option to throttlingOptions for simulating offline
network conditions
- Update emulate_network tool to handle offline mode with proper network
conditions
- Update documentation to include offline option and usage instructions
- Add test coverage for offline network emulation functionality
- Enable testing of PWA and offline-first web applications through MCP
PR Description
- Fix the stop-trace guard to call context.isRunningPerformanceTrace()
so we skip page.tracing.stop() when nothing is recording, avoiding the
Puppeteer error that bubbled up
to users.
- Extend the “does nothing” test to stub tracing.stop() and assert it
stays untouched, guaranteeing the guard path is covered.
We were setting the storage inside the first collect callback which mean
that we double subscribed to the events.
This affected Network request and Console messages
## Summary
This PR adds WebP format support to the screenshot tool, providing
superior compression compared to JPEG while maintaining image quality.
## Problem
Currently, the Chrome DevTools MCP only supports PNG and JPEG formats
for screenshots. This leads to:
- Missing out on WebP's superior compression (25-34% better than JPEG at
equivalent quality)
- Larger file sizes than necessary for AI assistants with image size
limits
- No access to a modern format that offers both better compression and
transparency support
- Bug: `saveTemporaryFile` always saved files with `.png` extension
regardless of the specified format
## Solution
Added WebP as a supported format in the screenshot tool schema and
extended the quality parameter to work with WebP (0-100 range, same as
JPEG). Also fixed the file extension bug in `saveTemporaryFile`.
## Changes
- ✅ Added `webp` to screenshot format enum alongside `png` and `jpeg`
- ✅ Extended quality parameter description to include WebP support
- ✅ Updated `saveTemporaryFile` to properly handle WebP MIME type and
file extension
- ✅ Fixed bug where all screenshots were saved as `.png` regardless of
format
- ✅ Updated type definitions in `ToolDefinition.ts` for WebP support
- ✅ Updated documentation via `npm run docs`
## Testing
Puppeteer 24.22.3 (used by this project) has full WebP support including
quality parameter. Expected compression improvements based on WebP
benchmarks:
- **PNG (baseline):** 128 KB
- **JPEG quality 50:** 84 KB (34% reduction vs PNG)
- **WebP quality 50:** ~60 KB (53% reduction vs PNG, 29% better than
JPEG)
- **WebP quality 75:** ~90 KB (optimal quality/size balance)
All existing tests pass (131/131).
## Impact
This change is **backward compatible** - WebP is an optional format that
doesn't affect existing PNG/JPEG usage. It particularly helps with:
- AI assistants that have image size limits
- Reducing bandwidth when capturing many screenshots
- Providing transparency support with better compression than PNG
- Offering a modern, universally-supported image format (Chrome,
Firefox, Safari, Edge)
## Example Usage
```javascript
// High quality WebP
await take_screenshot({
format: 'webp',
quality: 85,
fullPage: false
})
// Optimized for size
await take_screenshot({
format: 'webp',
quality: 50, // ~29% smaller than JPEG quality 50
fullPage: true
})
```
## Checklist
- [x] Code follows conventional commits
- [x] Documentation updated with `npm run docs`
- [x] All tests passing (131/131)
- [x] Backward compatible
- [x] Bug fix included (file extension handling)
- [ ] CLA signed (will complete if needed)
Fixes #[issue-number] (if applicable)
---------
Co-authored-by: aberemia24 <aberemia@gmail.com>
Co-authored-by: Alex Rudenko <alexrudenko@chromium.org>
### Summary
This PR build upon #145 to also adds filtering by resource type to
`list_network_requests` (Also see: #137 and #107).
### Motivation
Agents often need specific request types (e.g., scripts, stylesheets,
images). Filtering reduces noise and improves performance.
### Changes
- **New parameter**: `resourceType` (array) to filter by resource types
- **Supported types**: all resource types supported by Puppeteer
- **Backward compatible**: when omitted, returns all requests
Filtering runs before pagination, so pagination applies to the filtered
results.
This CL adds the descriptions of the call frame format and the network
request format to the summary so that as the AI sees these responses it
can fully parse them.
This includes a better fix for the circular dependency problem and makes
the changes in the MCP server based on the upstream DevTools
implementation changes.
Alex Rudenko