Closes #119

JetBrains AI Assistant and Junie also support MCP, this PR describes the
necessary configuration.

---------

Co-authored-by: Sebastian Benz <sebastian.benz@gmail.com>
Co-authored-by: Sebastian Benz <sbenz@google.com>

Closes #125

This fixes the ImageDelivery insight which throws when we try to
generate it
because of its dependency on core/i18n. The long term fix here is to
remove the reliance of models/trace on the core/i18n package, or at
least dependency inject it, but this is a quick fix to at least make
this insight available.

The irony is that we don't even use the string in the AI output; but if
we don't have the method available we cannot generate the insight.

This fixes part of #124 by making this insight not error. The other
required work for that bug is to deal with Insights that do error. That
work is done in DevTools, but we need to ship & roll a new version into
the MCP server.

## Summary

This PR enhances the `list_network_requests` tool with pagination
support to handle large numbers of network requests efficiently. See
[this
issue](#136).

## Motivation

In my experience, the `list_network_requests` tool frequently hits LLM
token limits on pages with many requests, making it unusable for modern
web applications. I wanted to add pagination to allow agents to be more
flexible and manage token limits on their own.

## Changes

### Pagination Support
- Added `pageSize` parameter to limit requests per call
- Added `pageToken` parameter for navigation between pages
- Added pagination metadata in responses (nextPageToken,
previousPageToken, startIndex, endIndex, total)

### Implementation Details
- **New utility**: `src/utils/pagination.ts` - generic pagination
function
- **Enhanced McpResponse**: Added pagination options to
`setIncludeNetworkRequests()`
- **Updated network tool**: Added pagination parameters to schema
- **Offset-based pagination**: Uses numeric tokens, handles invalid
tokens gracefully

## Testing
- Comprehensive test coverage for pagination scenarios
- Tests for first page, subsequent pages, invalid tokens, and edge cases
- All existing tests continue to pass

## Backward Compatibility
- If no pagination parameters are provided, the MCP will return all
requests (same as before)

This commit updates DevTools to the latest release. This most
importantly includes a fix for #124 and other reported issues where
Insights that were actually errors were not handled correctly. They are
now formatted correctly on the DevTools side and now will not break
performance traces in the MCP server.

Fixes #148

🤖 I have created a release *beep* *boop*
---


##
[0.3.0](chrome-devtools-mcp-v0.2.7...chrome-devtools-mcp-v0.3.0)
(2025-09-25)


### Features

* Add pagination list_network_requests
([#145](#145))
([4c909bb](4c909bb))


### Bug Fixes

* avoid reporting page close errors as errors
([#127](#127))
([44cfc8f](44cfc8f))
* clarify the node version message
([#135](#135))
([0cc907a](0cc907a))
* do not set channel if executablePath is provided
([#150](#150))
([03b59f0](03b59f0))
* **performance:** ImageDelivery insight errors
([#144](#144))
([d64ba0d](d64ba0d))
* roll latest DevTools to handle Insight errors
([#149](#149))
([b2e1e39](b2e1e39))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).