Web Search API Eval
NPM · WEBSEARCH-API-EVAL-MCP · 2 COMPONENTS
Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.
Available components
Last scanned (49 minutes ago)
Scores higher than 31% of npm servers
Category Search and Retrieval
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 4.6.5, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 9 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability73
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1073 tokens (~89/item across 12 items; 12 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "run_live_search" implies "send" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 28 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- Security disclosure: unverified → fail ▼ functional
- 27 Oct 26 48
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/websearch-api-eval-mcp@1.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 94 packages
| Packages resolved | 94 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
compare_providers Compare providers ~117
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').
| Name | Type | Req | Description |
|---|---|---|---|
| metric_filter | string | – | Optional keyword to keep only matching metrics |
| providers | array | yes | Two or more of: You.com, Tavily, Exa, Parallel |
| use_case | string | – | overall, gtm, insurance or finance |
No output schema declared.
No examples provided.
fetch Fetch a benchmark document ~43
Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Document ID from search |
No output schema declared.
No examples provided.
get_charts Charts ~94
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.
| Name | Type | Req | Description |
|---|---|---|---|
| chart_id | string | – | e.g. overall_scorecard, finance_key_metrics, gtm_query_grid, time_steps_activation |
| use_case | string | – | Filter the list |
No output schema declared.
No examples provided.
get_methodology Methodology ~53
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_overall_results Overall results ~75
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_question Get a question ~80
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).
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Question ID, e.g. G3, I4 or F5 |
No output schema declared.
No examples provided.
get_scorecard Scorecard ~87
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.
| Name | Type | Req | Description |
|---|---|---|---|
| use_case | string | yes | overall, gtm, insurance or finance |
No output schema declared.
No examples provided.
how_to_run_locally Run it yourself ~39
How to rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_questions List questions ~63
The 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.
| Name | Type | Req | Description |
|---|---|---|---|
| use_case | string | – | all, gtm, insurance or finance |
No output schema declared.
No examples provided.
recommend_provider Recommend a provider ~89
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_need | string | – | What the agent does, e.g. 'voice agent answering in under a second' or 'finance research' |
No output schema declared.
No examples provided.
run_live_search Run a live search test ~149
Send one query to You.com, Tavily, Exa and Parallel right now, using the API keys set in your own environment (YDC_API_KEY, TAVILY_API_KEY, EXA_API_KEY, PARALLEL_API_KEY; providers without a key are skipped). Returns each provider's client-side latency, result count and top results. Calls use your own provider credits.
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Results per provider (1-10) |
| providers | array | – | Subset of You.com, Tavily, Exa, Parallel (default: all with a key) |
| query | string | yes | The search query, e.g. one of the benchmark's search calls |
No output schema declared.
No examples provided.
search Search the benchmark ~47
Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | What to look for |
No output schema declared.
No examples provided.
How do I install the Web Search API Eval MCP server?
Web Search API Eval runs locally as an npm package, launched with npx -y websearch-api-eval-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · websearch-api-eval-mcp
claude mcp add psinglap-websearch-api-eval -- npx -y websearch-api-eval-mcp
What is the Web Search API Eval MCP server?
Web Search API Eval is an MCP server listed in the public MCP registry as io.github.psinglap/websearch-api-eval. Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts. This page covers its npm package (websearch-api-eval-mcp).
Is the Web Search API Eval MCP server safe to use?
Web Search API Eval scores 63 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Web Search API Eval MCP server expose?
Web Search API Eval exposes 12 tools: get_overall_results, get_scorecard, compare_providers, recommend_provider, list_questions, and 7 more. Their descriptions and schemas cost roughly 936 tokens of context every time the server is loaded.
Is the Web Search API Eval MCP server still maintained?
Web Search API Eval is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Web Search API Eval MCP server under?
Web Search API Eval declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.