Web Search API Eval MCPサーバー

Web Search API Eval: MCP server

An MCP server that lets Claude, ChatGPT, Cursor and other AI assistants answer questions about the Web Search API Eval benchmark (You.com, Tavily, Exa and Parallel on 30 agent queries), and run your own live search spot checks.

Use it two ways:

	Hosted (no install)	Local (npm)
Connect	https://websearch-api-eval.psberkeleymba.workers.dev/mcp	npx -y websearch-api-eval-mcp
Works in	Claude, ChatGPT, any remote MCP client	Claude Desktop, Claude Code, Cursor, VS Code, any stdio MCP client
Benchmark tools	✅	✅
run_live_search with your own keys	—	✅

Install

Claude Code

claude mcp add websearch-api-eval -- npx -y websearch-api-eval-mcp

Claude Desktop, Cursor, VS Code (add to the client's MCP config):

{
  "mcpServers": {
    "websearch-api-eval": {
      "command": "npx",
      "args": ["-y", "websearch-api-eval-mcp"],
      "env": {
        "YDC_API_KEY": "optional",
        "TAVILY_API_KEY": "optional",
        "EXA_API_KEY": "optional",
        "PARALLEL_API_KEY": "optional"
      }
    }
  }
}

The keys are optional and only used by run_live_search. Leave out any provider you don't have a key for. Requires Node.js 18 or later.

Hosted, no install: in Claude, Settings → Connectors → Add custom connector → paste the hosted URL. In ChatGPT, create an app in Developer mode with the same URL and no authentication.

Tools

Tool	Returns
get_overall_results	Headline, overall scorecard, per-use-case summary, which API fits which agent, developer activation
get_scorecard	Full scorecard for overall, gtm, insurance or finance
compare_providers	Two or more providers side by side, optionally filtered by metric keyword
recommend_provider	Which API fits an agent's need, with supporting numbers
list_questions	The 30 questions, filterable by use case
get_question	One question: task, search call, answer key, sources, what each API returned and its score
get_charts	The published graphs; with chart_id, also the image
get_methodology	How tests ran and were graded, the 10 metrics and their standards, limits
how_to_run_locally	Steps and keys to rerun the full benchmark on your own machine
search, fetch	Generic search and document fetch (used by ChatGPT research features)
run_live_search (local only)	Sends one query to each provider using your own API keys and returns latency, result count and top results

The benchmark tools are read-only and read the published results (run Oct 8, 2026). run_live_search calls the providers directly from your machine with your keys and uses your own credits; a single call is a spot check, not a graded benchmark. For the full graded run, use the harness.

Example questions

• "Which web search API is fastest for a voice agent?"
• "Compare Exa and Parallel on finance."
• "What was question F5 and who got it right?"
• "Show me the overall scorecard chart."
• "Run a live search for 'FOMC minutes' and compare the providers."

Data and updates

Results come from data/*.json on the published site, built from the Evaluation page by data/build_data.py. After a new benchmark run, rebuild the data and push; both the hosted and npm servers pick it up with no redeploy or new release.

Develop

cd mcp
npm install
npx wrangler dev        # hosted server locally at http://localhost:8787/mcp
npm run build           # npm package entry at dist/cli.js
npx @modelcontextprotocol/inspector@0.17.2 node dist/cli.js   # call tools by hand
npx wrangler deploy     # deploy the hosted server
npm publish             # publish the npm package

Built with the official MCP TypeScript SDK. Registry entry: io.github.psinglap/websearch-api-eval (server.json).

Privacy and support

No sign-in, no cookies, no storage, no request logging. Privacy Policy · Terms · Support · MIT License