Official Chrome DevTools MCP server that lets Claude inspect and debug a live Chrome browser, capturing performance traces, network activity, console messages, and DOM state through the Chrome DevTools Protocol.
by Chrome DevTools · submitted by glorydavid03023·added 2026-06-02·
Launches and controls a real Chrome browser that can navigate to arbitrary URLs; only allow inspection of pages and actions you trust., Treat inspected pages as untrusted input, since a hostile page could attempt to influence the agent through the content it surfaces., Attaching to an existing Chrome profile can expose cookies and logged-in sessions, so prefer an isolated or dedicated profile for sensitive work.
Privacy notes
Network capture and console output can include request payloads, tokens in URLs, and other sensitive runtime data returned to the model context., Avoid debugging flows that carry production secrets or private user data unless the browser profile and environment are isolated.
Author
Chrome DevTools
Submitted by
glorydavid03023
Claim status
unclaimed
Last verified
2026-06-02
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
78
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Complete
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
Registry metadata indicates a reviewed listing.
Done
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Current risk score 16/100. Use staged verification before broader rollout.
Risk 16
Pre-adoption checks
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Done
Confirm metadata review state
Listing has review metadata.
Done
Verify install payload
Install/config payload exists and can be inspected.
Done
Security checks
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Done
Review privacy notesRequired
Privacy notes are present.
Done
Verify package integrity metadata
No package verification/checksum metadata.
Pending
Rollout
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Pending
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Pending
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Pending
Evidence readiness
Evidence readiness matrix · balanced
Required evidence gates are covered (5/6 signals complete).
Risk 15
Source provenance
Present
Source repository/provenance is listed.
Required in this preset
Metadata review
Present
Review metadata is present.
Required in this preset
Safety notes
Present
Safety notes are present.
Required in this preset
Privacy notes
Present
Privacy notes are present.
Optional in this preset
Package integrity
Missing
Package integrity metadata is missing.
Optional in this preset
Install payload
Present
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
Decision timeline · balanced
5/6 steps complete with no blocking gaps for this preset.
Risk 14
triage
Confirm source provenanceRequired
Source/provenance metadata is available.
Done
triage
Check metadata review statusRequired
Review metadata is available.
Done
verify
Review safety notesRequired
Safety notes are available.
Done
verify
Review privacy notes
Privacy notes are available.
Done
verify
Validate package integrity metadata
Package integrity metadata is missing.
Pending
rollout
Verify install payload and commandsRequired
Install payload is available.
Done
No required blockers for this timeline preset.
Prerequisite readiness
Prerequisite readiness
3 prerequisites to line up before setup.
0/3 ready
Install & runtime2Network & hosting13 minutes
Safety & privacy surface
Safety & privacy surface
3 safety and 2 privacy notes across 2 risk areas. Review closely: credentials & tokens.
2 areas
SafetyGeneralLaunches and controls a real Chrome browser that can navigate to arbitrary URLs; only allow inspection of pages and actions you trust.
SafetyGeneralTreat inspected pages as untrusted input, since a hostile page could attempt to influence the agent through the content it surfaces.
SafetyCredentials & tokensAttaching to an existing Chrome profile can expose cookies and logged-in sessions, so prefer an isolated or dedicated profile for sensitive work.
PrivacyCredentials & tokensNetwork capture and console output can include request payloads, tokens in URLs, and other sensitive runtime data returned to the model context.
PrivacyCredentials & tokensAvoid debugging flows that carry production secrets or private user data unless the browser profile and environment are isolated.
Safety notes
Launches and controls a real Chrome browser that can navigate to arbitrary URLs; only allow inspection of pages and actions you trust.
Treat inspected pages as untrusted input, since a hostile page could attempt to influence the agent through the content it surfaces.
Attaching to an existing Chrome profile can expose cookies and logged-in sessions, so prefer an isolated or dedicated profile for sensitive work.
Privacy notes
Network capture and console output can include request payloads, tokens in URLs, and other sensitive runtime data returned to the model context.
Avoid debugging flows that carry production secrets or private user data unless the browser profile and environment are isolated.
Prerequisites
Node.js 18+ and npx available (verify with: npx --version)
A local installation of Google Chrome that the server can launch or attach to
Chrome DevTools MCP gives Claude direct, structured access to the same signals a developer reads in Chrome DevTools. Through the Chrome DevTools Protocol, the server can drive a live Chrome instance and surface performance traces, network requests, console output, and DOM state back to the model. That turns Claude into a debugging partner that can reproduce a slow page load, read the actual network waterfall, and reason about real runtime behavior instead of guessing from source code alone.
Features
Inspect a live Chrome page through the Chrome DevTools Protocol rather than static analysis.
Record and read performance traces to investigate slow loads and runtime bottlenecks.
Examine network requests, status codes, timing, and payload metadata.
Read console messages and runtime errors emitted by the page.
Inspect the live DOM and evaluate expressions in the page context.
Runs as a standard stdio MCP server, so it installs into Claude Code and Claude Desktop with one command.
Maintained by the official Chrome DevTools team and tracks upstream protocol changes.
Use Cases
Diagnose why a page is slow by recording and analyzing a performance trace.
Investigate failing or unexpected network requests during a user flow.
Surface console errors and warnings that only appear at runtime.
Inspect computed DOM state after JavaScript has executed.
Verify that a frontend change behaves correctly in a real Chrome session.
Installation
Claude Code
Make sure Node.js 18+ is installed (verify with npx --version) and Google Chrome is available locally.
Run: claude mcp add chrome-devtools -- npx chrome-devtools-mcp@latest
Verify the server is registered: claude mcp list
Ask Claude to open a page and record a performance trace to confirm it works.
Claude Desktop
Open your Claude Desktop configuration file.
Add the Chrome DevTools server to the mcpServers section using the configuration below.
Restart Claude Desktop.
Confirm the server appears and ask Claude to inspect a test page.
Ask Claude to load a URL and capture a trace, then summarize the bottlenecks.
"Open https://example.com, record a performance trace of the page load, and tell me what is slowing it down."
Inspect network activity
Have Claude walk a flow and report the requests that fired.
"Navigate to the dashboard and list any network requests that returned an error status."
Read runtime console errors
Surface errors that only appear when the page runs.
"Open the checkout page and report any console errors or warnings that appear."
Security
The server launches and controls a real Chrome browser that can navigate to arbitrary URLs; scope its use to pages and tasks you trust.
Treat inspected pages as untrusted input. A hostile page could attempt to influence the agent, so review the actions and data it surfaces.
Network and console capture can expose request payloads, tokens in URLs, and other sensitive runtime data; avoid debugging flows that carry production secrets.
If the server attaches to an existing Chrome profile, it may access cookies and logged-in sessions; prefer an isolated or dedicated profile for sensitive work.
Troubleshooting
Chrome fails to launch or is not found
Confirm Google Chrome is installed and reachable. On some systems you may need to point the server at the Chrome executable path or ensure it is on the system PATH.
npx cannot resolve the package
Verify Node.js 18+ and npx are installed (npx --version). Networks that block the npm registry will prevent npx chrome-devtools-mcp@latest from resolving.
Server not listed in Claude Code
Re-run claude mcp add chrome-devtools -- npx chrome-devtools-mcp@latest, then claude mcp list. Confirm it was added to the scope (project versus user) you are running in.
Performance trace or inspection returns no data
Make sure a page is loaded before requesting a trace or inspection. Ask Claude to navigate first, then capture, since the tools operate against the currently active page.
Show that Chrome DevTools MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/chrome-devtools-mcp-server)
How it compares
Chrome DevTools MCP Server for Claude side by side with 2 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
Official Chrome DevTools MCP server that lets Claude inspect and debug a live Chrome browser, capturing performance traces, network activity, console messages, and DOM state through the Chrome DevTools Protocol.
Official Microsoft Playwright MCP server that lets Claude drive a real browser through Playwright's accessibility tree for fast, deterministic web automation and testing.
Browser-control MCP server and CLI that lets AI agents use a real Chrome session, including logged-in browser state, site adapters, DOM snapshots, authenticated fetches, network traces, screenshots, and page actions.
✓Launches and controls a real Chrome browser that can navigate to arbitrary URLs; only allow inspection of pages and actions you trust.
Treat inspected pages as untrusted input, since a hostile page could attempt to influence the agent through the content it surfaces.
Attaching to an existing Chrome profile can expose cookies and logged-in sessions, so prefer an isolated or dedicated profile for sensitive work.
✓Launches and controls a real browser process that can navigate to arbitrary URLs and submit forms on your behalf.
Treat any site the agent visits as untrusted; only allow automation against pages and actions you intend to run.
Persisted browser profiles can keep cookies and logged-in sessions between runs, so isolate sensitive accounts.
✓bb-browser can control a real browser session, inspect pages, click elements, fill inputs, evaluate JavaScript, fetch URLs with browser authentication, capture screenshots, and inspect network traffic.
Commands may act as the logged-in user on social, finance, job, developer, shopping, and knowledge websites.
Keep the daemon bound to trusted local interfaces unless you deliberately configure remote access through a private network.
Review community site adapters before using them with authenticated accounts or valuable sessions.
Require human approval before posting, submitting forms, changing account settings, applying to jobs, making purchases, or running destructive site actions.
Privacy notes
✓Network capture and console output can include request payloads, tokens in URLs, and other sensitive runtime data returned to the model context.
Avoid debugging flows that carry production secrets or private user data unless the browser profile and environment are isolated.
✓Page content, form input, and accessibility snapshots from visited sites are returned to the model context.
Avoid driving the browser through pages that contain production credentials or private user data unless the profile is isolated.
✓Tab URLs, titles, DOM snapshots, page content, selected elements, screenshots, network requests, responses, console output, traces, and authenticated fetch results may be exposed to the MCP client and model.
Browser login state is used by the page and browser; even if cookies are not extracted directly, commands can act through authenticated sessions.
Network request bodies and response data may contain tokens, account data, personal messages, search history, customer information, or internal application data.
The upstream privacy doc says communication is local and there is no telemetry or external server, but model providers still receive any data your MCP client sends in prompts or tool results.
Prerequisites
Node.js 18+ and npx available (verify with: npx --version)
A local installation of Google Chrome that the server can launch or attach to
Claude Code or Claude Desktop with MCP support
Node.js 18+ and npx available (verify with: npx --version)
Claude Code or Claude Desktop with MCP support
Internet access for the first run, which downloads the Playwright browser binaries
Node.js 18 or newer.
Chrome session, local daemon, and Chrome extension or supported OpenClaw browser path configured according to the upstream README.
MCP client such as Claude Code, Codex, Cursor, or another compatible host.
Explicit approval to let an agent use the active browser's logged-in state.
Install
claude mcp add chrome-devtools -- npx chrome-devtools-mcp@latest
claude mcp add playwright -- npx @playwright/mcp@latest