mcpbeat Sign in

Web Search API Eval MCP Server

answering

Web Search API Eval is answering right now. Last checked 6 min ago. 356 installs a week from npm. It exposes 11 tools. Last commit 27 Oct 2026.

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

Installs per day peak 310 · avg 10
a month agotoday
Uptime history 5 days of history
5 days agonow
100.0%
Uptime 24h
92 of 92 checks
11
Tools
read from the server
145 ms
Response time
average over 24h
356
Installs / week
npm and PyPI

What the code does

We read the source, 3 d ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Page executes code built at runtime accounts/index.html:268
  cards.innerHTML=out.map(([r,g])=>card(r,g)).join('');

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

run in your terminal
claude mcp add websearch-api-eval --transport http https://websearch-api-eval.psberkeleymba.workers.dev/mcp
Settings → Connectors → Add custom connector, then paste this address
https://websearch-api-eval.psberkeleymba.workers.dev/mcp
~/.codex/config.toml
[mcp_servers.websearch-api-eval]
url = "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "websearch-api-eval": {
      "url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "websearch-api-eval": {
      "type": "http",
      "url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
    }
  }
}

Available tools 11

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

charts
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 with titles and image links; with chart_id, also returns the image.
compare
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 keyword (e.g. 'latency', 'accuracy', 'fresh', 'cost', 'empty').
fetch
fetch
Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).
how
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.
methodology
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 and the standards they follow, and limits.
overall
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 calls, latency p50/p95, cost per correct answer. Also the per-use-case summary, which API fits which agent, and developer activation time.
question
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 (0-2, mean of 3 runs).
questions
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.
recommend
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 use case (GTM, insurance, finance). Returns the guidance with the supporting numbers.
scorecard
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, accuracy, freshness (% in window, newest relevant result age), content in one call, tokens, search cost.
search
search
Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.

Endpoints

URLTransportStateLatencyChecked
https://websearch-api-eval.psberkeleymba.workers.dev/mcp streamable-http answering 153 ms 6 min ago

Alternatives to Web Search API Eval

same job, measured the same way
Parallel Search MCP
by parallel

The best web search for your AI Agent

answering
Dipper
by dipper-search

Web search and page fetch for AI agents. Results come from a shared cache; cached calls cost less.

2 tools answering
Exa
by exa

Connect AI agents to Exa for web search, content fetching, and multi-step research.

2 tools answering
Linkup
by mcparmory

Search the web and fetch pages with sourced results, optimized for AI agents

212 installs/wk local only
P
Payx Tavily Search
by swathi-muralisrinivasan

FastMCP server for Tavily search API with web search and content extraction

local only
Siftdog
by khsarvar

Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.

52 installs/wk local only
You.com Web Access & AI
by youdotcom-oss

Web search, AI agent, and content extraction via You.com APIs

1 597 installs/wk 6 tools answering
Sifthound
by khsarvar

Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.

local only

Web Search API Eval — questions

Answers built from our own checks of this server.

What can Web Search API Eval do?
It exposes 11 tools, read directly from the server on our last check. Among them: compare_providers, fetch, get_charts, get_methodology, get_overall_results, get_question and 5 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Web Search API Eval working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 145 ms. The bar chart above shows every period we have measured.
How do I connect Web Search API Eval?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Web Search API Eval need an API key?
No. Web Search API Eval completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 11 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Web Search API Eval?
It answers our handshake in 145 ms on average, which is faster than 84% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Web Search API Eval?
The npm package websearch-api-eval-mcp was installed 356 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Web Search API Eval open source?
The code is open source: it is published under the MIT licence, written in HTML, 0 stars on GitHub and 1 open issue. The licence covers the code in the repository, not the hosted service at websearch-api-eval.psberkeleymba.workers.dev, which runs on its operator's own terms.