{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_5akv2mut7m9q","handle":"browser-runtime-mcp","url":"https://wellknown.network/agents/browser-runtime-mcp","links":{"self":"https://wellknown.network/agents/browser-runtime-mcp/record.json","html":"https://wellknown.network/agents/browser-runtime-mcp","markdown":"https://wellknown.network/agents/browser-runtime-mcp/record.md","api":"https://wellknown.network/api/v1/agents/browser-runtime-mcp","status":"https://wellknown.network/api/v1/agents/browser-runtime-mcp/status","claim":"https://wellknown.network/agents/browser-runtime-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/browser-runtime-mcp/claim.json","badge":"https://wellknown.network/agents/browser-runtime-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/browser-runtime-mcp/history","tools":"https://wellknown.network/api/v1/agents/browser-runtime-mcp/tools"},"ard":{"identifier":"urn:air::server:browser-runtime-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"browser-runtime-mcp","summary":"MCP server that gives AI agents real-time access to browser runtime errors, console logs, and page diagnostics via a Chrome Extension.","description":"# Browser Runtime MCP\n\nGive AI agents real-time access to browser runtime errors, console logs, and page diagnostics.\n\n**The problem:** AI coding agents can read your source code but are blind to what actually happens in the browser — runtime errors, console warnings, failed API calls, CSS rendering issues. You end up copy-pasting DevTools output back and forth.\n\n**The solution:** A Chrome Extension captures browser events and streams them to a local MCP server. Your AI agent (Claude Code, Cursor, etc.) can query errors, console logs, and page state directly through MCP tools.\n\n```\nBrowser tab → Chrome Extension → localhost MCP server → AI agent\n```\n\n## Quick Start\n\n### 1. Install the MCP server\n\n```bash\npip install browser-runtime-mcp\n```\n\n### 2. Install the Chrome Extension\n\nDownload the `extension/` folder from this repo, then:\n\n1. Open `chrome://extensions`\n2. Enable **Developer mode**\n3. Click **Load unpacked** → select the `extension/` folder\n\n### 3. Configure your AI tool\n\n**Claude Code** — add to `~/.claude/settings.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"browser-runtime-mcp\": {\n      \"command\": \"browser-runtime-mcp\",\n      \"args\": []\n    }\n  }\n}\n```\n\n**Other MCP clients** — run the server in stdio mode:\n\n```bash\nbrowser-runtime-mcp\n```\n\n### 4. Use it\n\nOpen the extension popup on the site you want to debug and click **Enable capture on this site**.\nCapture is disabled by default and the allowlist is stored locally in Chrome. Then ask your AI agent:\n\n- \"Are there any browser errors?\"\n- \"What's in the console logs?\"\n- \"What pages is the extension tracking?\"\n\n## MCP Tools\n\n| Tool | Description |\n|------|-------------|\n| `get_browser_errors` | Runtime errors with stack traces and DOM context |\n| `get_console_logs` | Console output (error/warn/log), filterable by level |\n| `get_page_info` | Tracked pages and buffer statistics |\n| `clear_buffers` | Clear all buffered data for a fresh start |\n\n## How It Works\n\n```\n┌─────────────────┐     postMessage      ┌───────…","publisher":null,"homepage":"https://github.com/MakiDevelop/browser-runtime-mcp","repository":"https://github.com/MakiDevelop/browser-runtime-mcp","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["ai-agent","browser","chrome-extension","debugging","devtools","mcp"],"pricing":null,"endpoints":[{"url":"pypi:browser-runtime-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"code.debugging","name":"Debugging","confidence":1,"provenance":"declared"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"declared"}],"categories":["code","infra"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"browser-runtime-mcp","registry":"pypi","observedAt":"2026-11-02T23:25:17.298Z","publishedAt":"2026-08-07T08:14:30.677378Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"browser-runtime-mcp","url":"https://pypi.org/project/browser-runtime-mcp/","firstSeenAt":"2026-09-09T10:27:54.677Z","fetchedAt":"2026-11-02T23:23:06.399Z","normalizedAt":"2026-11-02T23:23:06.399Z"}]},"firstSeenAt":"2026-09-09T10:27:54.677Z","updatedAt":"2026-11-02T23:25:17.298Z"}