Support

The Web Search API Eval MCP server lets Claude, ChatGPT and other AI assistants answer questions about the benchmark: scorecards, provider comparisons, the 30 queries and their answer keys, charts, methodology and how to rerun it.

Connect

Server URL: https://websearch-api-eval.psberkeleymba.workers.dev/mcp · Streamable HTTP · no sign-in.

• Claude: Settings → Connectors → Add custom connector → paste the URL.
• ChatGPT: Plugins/Apps → Create (Developer mode) → paste the URL → No authentication.
• Claude Code: claude mcp add --transport http websearch-api-eval https://websearch-api-eval.psberkeleymba.workers.dev/mcp

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.
• How do I run this benchmark on my own queries?

Get help or report a problem

Open an issue at https://github.com/psinglap/websearch-api-eval/issues. Include the question you asked and what the assistant returned.

Documentation

MCP server docs · README · Privacy Policy · Terms of Service