Web Search API Eval

io.github.psinglap/websearch-api-evalpsinglapstreamable-httpv1.0.0Scanned 40 minutes ago

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

11 tools: 2 change things and 9 only read.

Reads private data · 1
Reads text others write · 1
Can send data out · 0
1 finding

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

11 tools

Changes things 2Creates or changes something that can be changed back.Claude Code: ask

how_to_run_locallyHow to rerun this benchmark on your own machine with your own API keys, including on your own queries.1 finding
Why it is in this group
- The name "how_to_run_locally" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "how_to_run_locally" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "how_to_run_locally" says "run": a word for a change.
  What this check looks for
Description, as the server wrote it
How to rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Run it yourself
recommend_providerWhich 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, insuran…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Recommend a provider

Only reads 9Looks things up and changes nothing.Show 9 read-only tools

compare_providersCompare 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.No findings
Why it is in this group
- The name "compare_providers" says "compare": a word for reading.
Description, as the server wrote it
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').
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Compare providers
fetchFull text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).Reads private dataNo findings
Why it is in this group
- The name "fetch" says "fetch": a word for reading.
What it can reach
- private-dataThe description's first sentence says "document": it reads documents.
Description, as the server wrote it
Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Fetch a benchmark document
get_chartsThe published graphs: overall scorecard, key metrics and per-query grids for GTM, insurance and finance, and developer activation.No findings
Why it is in this group
- The name "get_charts" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Charts
get_methodologyHow 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 t…No findings
Why it is in this group
- The name "get_methodology" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Methodology
get_overall_resultsHeadline 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/p9…No findings
Why it is in this group
- The name "get_overall_results" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Overall results
get_questionOne benchmark question by ID (e.g.No findings
Why it is in this group
- The name "get_question" says "get": a word for reading.
Description, as the server wrote it
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).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get a question
get_scorecardFull metric scorecard for one use case (gtm, insurance, finance) or 'overall'.No findings
Why it is in this group
- The name "get_scorecard" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Scorecard
list_questionsThe 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.No findings
Why it is in this group
- The name "list_questions" says "list": a word for reading.
Description, as the server wrote it
The 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: List questions
searchSearch the Web Search API Eval benchmark (results, questions, methodology, charts, how to run).Reads text others writeNo findings
Why it is in this group
- The name "search" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it
Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Search the benchmark

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1: Reads files, mail, messages, databases, secrets, calendars or repositories.; fetch
Reads text others write1: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; search
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

1 warn

Warnhow_to_run_locally
The server marks "how_to_run_locally" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "how_to_run_locally" says "run": a word for a change.
What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__websearch-api-eval__get_overall_results",
      "mcp__websearch-api-eval__get_scorecard",
      "mcp__websearch-api-eval__compare_providers",
      "mcp__websearch-api-eval__list_questions",
      "mcp__websearch-api-eval__get_question",
      "mcp__websearch-api-eval__get_charts",
      "mcp__websearch-api-eval__get_methodology",
      "mcp__websearch-api-eval__search",
      "mcp__websearch-api-eval__fetch"
    ],
    "ask": [
      "mcp__websearch-api-eval__recommend_provider",
      "mcp__websearch-api-eval__how_to_run_locally"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as websearch-api-eval. Review it before you use it.

Capability tags behind 2 rules

mcp__websearch-api-eval__search untrusted-input
mcp__websearch-api-eval__fetch private-data

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/io.github.psinglap/websearch-api-eval/verify?hash=1560666d7d27136ce6922eb5002d1c356c8fcc3fcab9c465d34191ff9f23ba3c" | jq -e '.changed == false'

Pinned hash 1560666d7d27, from Oct 27, 2026, 03:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.psinglap/websearch-api-eval/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.psinglap/websearch-api-eval.svg)](https://anlyon.dev/servers/io.github.psinglap/websearch-api-eval)

Source: MCP Registry · repository. Synced Oct 27, 2026, 03:17 UTC.