Docs Mcp Eval MCP Server
@speakeasy-api/docs-mcp-eval
npm
v0.19.1
Source verified
Published by speakeasy-api — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Evaluation and benchmarking harness for docs-mcp search quality metrics
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 6
high Shell/command execution in server code (dist/agent/assertions.js)MTC-SRC-002
In the server's implementation (`dist/agent/assertions.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { readFile } from "node:fs/promises"; import { join } from "node:path"; i
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/agent/assertions.js
high Shell/command execution in server code (dist/agent/build-cache.js)MTC-SRC-002
In the server's implementation (`dist/agent/build-cache.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from "node:child_process"; const PROJECT_ROOT = path.resolve(path.dirname(fileURLToPath(import.meta.url)),
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/agent/build-cache.js
high Shell/command execution in server code (dist/agent/provider-codex.js)MTC-SRC-002
In the server's implementation (`dist/agent/provider-codex.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from "node:child_process"; import { readFile } from "node:fs/promises"; import { homedir } from "node:os";
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/agent/provider-codex.js
high Shell/command execution in server code (dist/agent/repo-cache.js)MTC-SRC-002
In the server's implementation (`dist/agent/repo-cache.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from "node:child_process"; const PROJECT_ROOT = path.resolve(path.dirname(fileURLToPath(import.meta.url)),
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/agent/repo-cache.js
high Shell/command execution in server code (dist/agent/runner.js)MTC-SRC-002
In the server's implementation (`dist/agent/runner.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { mkdir, mkdtemp, readFile, rm, symlink } from "node:fs/promises"; import
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/agent/runner.js
high Shell/command execution in server code (dist/runner.js)MTC-SRC-002
In the server's implementation (`dist/runner.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ile, spawn } from "node:child_process"; import { performance } from "node:perf_hooks"; import { promisify } from "node:u
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/runner.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 5
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.19.1 latest |
A 94/100 | 6 | 1.13.0 | 2026-09-07 |
v0.18.0 |
A 94/100 | 6 | 1.13.0 | 2026-09-04 |
v0.17.1 |
A 94/100 | 6 | 1.13.0 | 2026-09-01 |
v0.17.0 |
A 94/100 | 6 | 1.12.1 | 2026-07-31 |
v0.16.3 |
A 94/100 | 6 | 1.12.1 | 2026-07-27 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @speakeasy-api/docs-mcp-eval --onlineMore in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai