Web Search API Eval for Claude.ai

io.github.psinglap/websearch-api-eval

Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.

client:Claude.ai transport:streamable-http tools:11

Install Web Search API Eval in Claude.ai

Settings → Connectors → Add custom connector

https://websearch-api-eval.psberkeleymba.workers.dev/mcp

Claude on the web takes a remote URL and completes OAuth in the browser. For a packaged server use Claude Desktop or Claude Code instead. Claude.ai docs

What Claude.ai can do once it is connected

get_overall_results
get_scorecard
compare_providers
recommend_provider
list_questions
get_question
get_charts
get_methodology
how_to_run_locally
search
fetch

Web Search API Eval in other clients

Claude Code
Claude Desktop
Cursor
VS Code
Zed
Windsurf
Cline
Gemini CLI
Grok
ChatGPT
LangChain

Web Search API Eval MCP server