chrome-devtools-mcp-bridge
Skill1 starsChanged 23 days agoMITView on GitHub
Drive a Chrome DevTools MCP server for browser automation, network traces, console capture, and performance audits. Use when a web page must be inspected or exercised through the DevTools Protocol instead of a headless script.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- .gemini/AGENTS.mdAGENTS.md
- .cursor/rules/agent-foundry-orchestrator.mdcCursor rule
- .cursor/rules/agent-foundry-skills.mdcCursor rule
- web/llms.txtllms.txt
- anti-slopSkill
- api-designSkill
- automation-pickSkill
- bottleneck-gatingSkill
- budget-guardSkill
- cache-identitySkill
- constraint-then-solveSkill
- context-optimizationSkill
- cron-troubleshootSkill
- e2e-test-strategySkill
- engram-routingSkill
- execution-observabilitySkill
- fallback-model-routingSkill
- feedback-loopSkill
- judge-integritySkill
- knowledge-extractSkill
- landscape-firstSkill
- measure-firstSkill
- plan-before-codeSkill
- plan-then-actSkill
- prompt-disciplineSkill
- pushback-when-wrongSkill
- quality-protocolSkill
- read-before-buildSkill
- re-verify-findingsSkill
- session-closeoutSkill
- session-distillSkill
- show-your-workSkill
- structured-output-contractSkill
- verify-firstSkill
- workflow-decomposeSkill
- agent-memory-vaultSkill
- agent-team-standardsSkill
- autonomous-briefingSkill
- book-to-skillSkill
- design-languageSkill
- funnel-pr-guardSkill
- persistent-memorySkill
- sql-migration-trioSkill
- token-compressionSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Start Chrome so the server can attach, or let the server manage the browser.
- Distinctive: line 27
Treat tool names and arguments as version-specific: read the live tool list rather than assuming a fixed catalog.
- Distinctive: line 34
After each action, re-snapshot and check console and network for errors.
- Distinctive: line 35
Use screenshots for visual claims.
- Distinctive: line 36
Start a performance trace before the interaction and stop it after, then analyze the result.
- Distinctive: line 55
Use this server for web pages, DevTools, network, and console.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Chrome DevTools MCP Bridge
Guidance for using the external Chrome DevTools MCP server from an
MCP-capable client. The upstream project is ChromeDevTools/chrome-devtools-mcp
(Apache-2.0). It is not vendored or redistributed here; install and license it
under its own terms.
Procedure
Prerequisites
- Install and run the MCP server by following its upstream README.
- Start Chrome so the server can attach, or let the server manage the browser.
- Register the server in your MCP client and confirm it lists tools.
- Treat tool names and arguments as version-specific: read the live tool list rather than assuming a fixed catalog.
Workflow
- Navigate, then take an accessibility snapshot before acting.
- Act through the snapshot's element references, not guessed coordinates.
- After each action, re-snapshot and check console and network for errors.
- Use screenshots for visual claims; use the DOM snapshot for structural ones.
- Start a performance trace before the interaction and stop it after, then analyze the result.
Capability areas
| Area | Typical operations |
| Pages | navigate, create, select, close |
| Inspection | accessibility snapshot, screenshot, click, hover, fill, drag |
| Console | list messages, inspect one message |
| Network | list requests, inspect one request |
| Script | evaluate in page, type text, fill forms, press keys |
| Performance | start and stop traces, analyze insights, emulate device or network |
| Audit | Lighthouse-style audit, heap snapshot |
The exact set varies by server version. Confirm before scripting.
Separation from desktop automation
Use this server for web pages, DevTools, network, and console. Use a desktop automation tool for native windows. Do not use either where the other is the actual target.
Limits and safety
- The server can execute page scripts; scope it to test profiles and non-sensitive accounts.
- Network traces and snapshots may contain credentials or personal data. Redact before sharing.
- A failed connection usually means the browser was not started with debugging enabled or the client points at the wrong port.
- The repo does not test a specific server version; compatibility is your check.
Anti-patterns
- Using this for native-app automation.
- Clicking by pixel coordinates when a snapshot reference exists.
- Relying on a screenshot where the DOM would answer the question.
- Pasting raw network traces into a shared document without redaction.
Verification Checklist
- The MCP client lists the server's tools for the installed version.
- A snapshot reference, not a guess, was used for the interaction.
- Console and network were checked after the action.
- Traces and screenshots are redacted before sharing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

