how_to_run_locally — Web Search API Eval MCP Tool
how_to_run_locally
(how to run locally) is one of 11 tools on the
Web Search API Eval
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call how_to_run_locally from your client
- Claude Code Web Search API Eval how_to_run_locally run in your project directory
- Claude Desktop Web Search API Eval how_to_run_locally ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Web Search API Eval how_to_run_locally ~/.cursor/mcp.json
- VS Code Web Search API Eval how_to_run_locally .vscode/mcp.json
- Zed Web Search API Eval how_to_run_locally ~/.config/zed/settings.json
- Windsurf Web Search API Eval how_to_run_locally ~/.codeium/windsurf/mcp_config.json
- Cline Web Search API Eval how_to_run_locally ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Web Search API Eval how_to_run_locally ~/.gemini/settings.json
- Grok Web Search API Eval how_to_run_locally .mcp.json (in your project root)
- ChatGPT Web Search API Eval how_to_run_locally Settings → Connectors → Advanced → Developer mode
- Claude.ai Web Search API Eval how_to_run_locally Settings → Connectors → Add custom connector
- LangChain Web Search API Eval how_to_run_locally pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http websearch-api-eval https://websearch-api-eval.psberkeleymba.workers.dev/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 27 October 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.