Claude Desktop Web Search API Eval how_to_run_locally
How to: Claude Desktop Web Search API Eval how_to_run_locally
Add Web Search API Eval to Claude Desktop
-
01
Open ~/Library/Application Support/Claude/claude_desktop_config.json and merge this in. Keep any servers already there.
{
"mcpServers": {
"websearch-api-eval": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
]
}
}
}-
02
Save the file and restart Claude Desktop.
-
03
Ask for something how_to_run_locally does. Claude Desktop lists the server's tools on connect and calls how_to_run_locally itself — you do not invoke it by name.
-
04
If nothing happens, check the server is running and that Web Search API Eval's identifier in your config matches the one above exactly.
Claude Desktop has no remote transport in its config file, so this bridges through mcp-remote. Restart the app after saving. Claude Desktop docs
Same tool, other clients
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.