{"id":"vinayak-mehta-mcp-browser-use","name":"mcp-browser-use","af_score":31.8,"security_score":33.2,"reliability_score":30.0,"what_it_does":"Provides an MCP server that connects an MCP client (e.g., Claude/Cursor) to the browser automation capabilities of browser-use, allowing agents to control a browser through the MCP client while reusing the LLM already configured in that MCP client.","best_when":"You already have an MCP client configured with the desired LLM and want browser-use capabilities exposed to it via MCP.","avoid_when":"You cannot ensure the MCP client/host environment is secured, or you need clear guarantees about authentication, rate limiting, and data handling for this specific package.","last_evaluated":"2026-03-30T13:50:18.224779+00:00","has_mcp":true,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["Browser automation can be nondeterministic (timing, selectors, page changes). Agents may need robust retry/backoff at the task level.","Because auth/rate-limit/error semantics are not documented here, agent frameworks may need defensive handling (timeouts, reconnects, and conservative concurrency).","The README does not specify required environment variables or how the MCP client passes LLM/browser settings; misconfiguration may lead to startup/runtime failures."],"error_quality":0.0}