io.github.psinglap/websearch-api-eval

up checked 2026-11-11T10:39:28.383Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Web Search API Eval

Publisher-provided description

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

Summary by lookupd

Lets an agent query and compare benchmark results, methodology and charts for several web search APIs, and recommend one for a given task.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http websearch-api-eval https://websearch-api-eval.psberkeleymba.workers.dev/mcp

Claude Code, npm package (stdio)

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

Codex, remote (streamable-http)

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

Codex, npm package (stdio)

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

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "websearch-api-eval": {
      "url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
    }
  }
}

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "websearch-api-eval": {
      "command": "npx",
      "args": [
        "-y",
        "websearch-api-eval-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (11 tools)

Publisher-provided text

get_overall_results Headline findings and the overall scorecard across all 30 queries (90 calls per API): accuracy, fully correct, precision@5, freshness, empty responses, failed c
get_scorecard Full metric scorecard for one use case (gtm, insurance, finance) or 'overall'. Metrics: search-only latency p50/p95 (server and client), calls under 1 s, accura
compare_providers Compare two or more of You.com, Tavily, Exa and Parallel side by side, overall or within one use case, optionally filtered to metrics whose name contains a keyw
recommend_provider Which web search API fits an agent, based on this benchmark: live voice/chat turns, deep research, semantic or long-tail queries, docs lookups, or a specific us
list_questions The 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.
get_question One benchmark question by ID (e.g. G3, I4, F5): the task, search call, parameters, answer key with sources, and what each API returned with its accuracy score (
get_charts The published graphs: overall scorecard, key metrics and per-query grids for GTM, insurance and finance, and developer activation. Without chart_id, lists them
get_methodology How the benchmark was run and graded: query design, identical request parameters, 3 runs per query, latency timing, SimpleQA and FreshQA grading, the 10 metrics
how_to_run_locally How to rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.
search Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.
fetch Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).

Details

Version: 1.1.0
Transports: streamable-http, stdio
Uptime (7 days): 100%
Median latency: 313 ms
First indexed: 2026-11-01T09:50:08.853Z
Last seen in registry: 2026-11-01T09:50:08.864Z
Repository: https://github.com/psinglap/websearch-api-eval
Website: https://psinglap.github.io/websearch-api-eval/

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.psinglap/websearch-api-eval.svg)](https://lookupd.com/servers/io.github.psinglap/websearch-api-eval)

62071 servers
Last crawl: 2026-11-11T16:39:06.253Z
API base: https://api.lookupd.com
MCP URL: https://api.lookupd.com/mcp