feat: add Gemini CLI extension context for better tool usage#710
Closed
LyalinDotCom wants to merge 1 commit intoChromeDevTools:mainfrom
Closed
feat: add Gemini CLI extension context for better tool usage#710LyalinDotCom wants to merge 1 commit intoChromeDevTools:mainfrom
LyalinDotCom wants to merge 1 commit intoChromeDevTools:mainfrom
Conversation
Add gemini-extension.md as a system instruction file for Gemini CLI. When users install this extension, Gemini CLI will use this context to understand how to properly use the Chrome DevTools MCP tools. This enables Gemini CLI to respond intelligently to user requests like "test my web page" by knowing to: - Use take_snapshot() first to get element UIDs - Follow the snapshot-first workflow for interactions - Handle dynamic content and stale UIDs appropriately Updated gemini-extension.json with contextFileName property to reference the new context file. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
OrKoN
reviewed
Jan 7, 2026
|
|
||
| This extension enables you to control a real Chrome browser instance to inspect, debug, and automate web interactions via the Model Context Protocol (MCP). | ||
|
|
||
| ## Core Capabilities & Tools |
Collaborator
There was a problem hiding this comment.
Thanks! I think that the client already has the list of tools and their descriptions from the MCP server. Do you see the duplication of tool definitions as necessary or perhaps the ## Core Capabilities & Tools section can be removed?
theomart
pushed a commit
to theomart/chrome-devtools-mcp
that referenced
this pull request
Jan 15, 2026
Analyze GitHub issues (sorted by comments), PRs, and source code to document key technical challenges for building browser automation MCPs with AI agents. Key findings grounded in actual code: - Token explosion from automatic snapshots in input tools (src/tools/input.ts) - Error handling patterns learned from crashes (src/main.ts, src/PageCollector.ts) - WSL2 Chrome discovery issues (src/browser.ts) - Dual-format output implementation (src/formatters/SnapshotFormatter.ts) - Accessibility tree limitations from Puppeteer dependency Sources: Issues ChromeDevTools#131, ChromeDevTools#363, ChromeDevTools#617, ChromeDevTools#635, ChromeDevTools#689, ChromeDevTools#690, ChromeDevTools#709, ChromeDevTools#713, ChromeDevTools#716, ChromeDevTools#726, ChromeDevTools#752 PRs: ChromeDevTools#618, ChromeDevTools#710, ChromeDevTools#744 Commits: f59b4a2, ca0f560, 3fcca02
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add gemini-extension.md as a system instruction file for Gemini CLI, as suggested in #709.
Context
When users install this MCP server as a Gemini CLI extension extension, Gemini CLI will use this additional context in the markdown file provided to understand how to better use the Chrome DevTools MCP tools.
Updated gemini-extension.json with contextFileName property to reference the new context file.
Testing
This was tested with Gemini CLI as its not a direct edit to any of the functionality of the MCP server itself.