A
licenseNot graded
qualityB
maintenanceEnables AI coding agents to access live console logs, errors, and network requests from web applications via a local WebSocket connection, without copying data to chat.
2 npm
19
MIT
agentshot-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agentshot-mcpshow me the feedback I left on the page and reply to it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
agentshot-mcp
Local MCP server for the AgentShot Chrome extension. It lets an AI coding agent (Claude Code first) read the feedback you leave on web pages with AgentShot's AI Feedback mode, and reply to it.
It runs only on your computer: the bridge to the extension listens on 127.0.0.1, requires a token, and nothing is sent to any other service.
agentshot-mcp.mjs is a single bundled file (the server plus the MCP SDK and zod, see THIRD_PARTY_LICENSES.md). It is deliberately not minified, so you can read exactly what runs on your machine.
Privacy policy for AgentShot (extension and server): PRIVACY.md. Questions and bug reports: Issues.
Setup (Node.js 18+)
# 1. Add the server to Claude Code (one time)
claude mcp add agentshot -- npx -y github:Gautamvaishnav-git/agentshot-mcp
# 2. Start Claude Code in your project and keep it open
# 3. Print your token, paste it in AgentShot > Settings > Agent connection, press Connect
npx -y github:Gautamvaishnav-git/agentshot-mcp tokenRelated MCP server: Antigravity Browser Controller
Remove
npx -y github:Gautamvaishnav-git/agentshot-mcp --purge # delete stored feedback and screenshots
claude mcp remove agentshot
rm -rf ~/.agentshot # token and dataThis server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Comment on AI-generated webpages; feedback flows back to your coding agent. Free, MIT, local-first.
Connect AI agents to your own Chrome with scoped access, approvals, and verified task results.
Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.
Human feedback for AI agents: share HTML, get a live review link, read anchored notes as markdown.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to control a user's existing Chrome browser with preserved logins, performing tab management, element interaction, script execution, and screenshots, all locally via a Chrome extension and Python bridge.2MIT
- AlicenseBqualityBmaintenanceEnables AI coding agents to inspect and operate Chrome as a developer, including reading DevTools console/network data, evaluating JavaScript, and managing unpacked extensions during an edit-test-debug loop.24MIT
- AlicenseNot gradedqualityAmaintenanceLets AI coding tools drive the real, already-logged-in Chrome browser over local stdio—snapshotting and reading pages, clicking, typing, managing tabs, capturing screenshots, and inspecting network, console, storage, and cookies—without opening a remote-debugging port. It installs as a Chrome extension plus native-messaging bridge, so agents work in the user's authenticated sessions while passing bot detection.1 npmISC