TrustedMCP
TrustedMCP lets you grade and vet MCP servers and configs with read-only lookups, config checks, alternatives, and registry security data.
lookup_server: Get an A–D TrustedMCP grade for an MCP server by name, package, image, URL, repo, or launch command, including four checks, top fixes, and a page link; falls back to official registry matches if ungraded.check_config: Grade every server in an MCP config by reading common local configs, one client/path, or pasted JSON, while sending only package/image/URL identifiers.find_alternatives: List graded servers best-first, filtered by category, search term, minimum grade, or better options instead of a given server.registry_lookup: Fetch an official MCP Registry entry with packages, remotes, TrustedMCP grade, and GHSA/CVE security issues with affected-version info.All tools are read-only and require a free API key.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TrustedMCP check my MCP config and tell me what to fix first"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TrustedMCP MCP server
Give your agent the TrustedMCP grades. Ask it "is this MCP server any good?" or "check my MCP setup", and it answers with an A to D grade per server, what to fix first, and better-graded servers in the same category.
Each grade is an assessment from public signals: login, upkeep, known CVEs and how the server connects. Use it as a starting point for your own review. It is not an audit of the code. How we grade.
Tools
Tool | What it does |
| One server by name, npm or PyPI package, Docker image, URL, GitHub repo or launch command: its grade, the four checks, what to fix first, its TrustedMCP page. |
| Every server in your MCP config. With no arguments it reads the usual config files for Claude Desktop, Claude Code, Cursor, VS Code and Windsurf. You can also pass one |
| Graded servers by category, search term or minimum grade. Or |
| An official MCP Registry entry: packages, remotes, TrustedMCP grade if any, and reported security issues (GHSA/CVE, and whether the listed version is affected). |
All four tools only read data.
Related MCP server: repo-doctor
Get a key
Tool calls need a free API key. Sign up with your email at trustedmcp.io/developers. The server still starts and lists its tools without one, but every tool call returns an error that tells you to add a key.
Keys are scoped. A key can have any of these three scopes:
Scope | Covers |
|
|
|
|
|
|
registry_lookup also falls back to a server search when you give it a package name or search term instead of a registry name, so give the key servers:read as well. If a key lacks the scope a tool needs, the tool says which scope is missing. You can revoke or rotate a key on the same page. A revoked or invalid key is rejected, and the tool tells you to get a new one.
Install
Hosted (no install)
TrustedMCP also runs as a hosted server at https://trustedmcp.io/mcp. It has the same four tools. Nothing to install, no Node.js needed. Send your key as a Bearer token.
Claude Code:
claude mcp add --transport http trustedmcp https://trustedmcp.io/mcp --header "Authorization: Bearer YOUR_KEY"Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"trustedmcp": {
"url": "https://trustedmcp.io/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}VS Code (.vscode/mcp.json):
{
"servers": {
"trustedmcp": {
"type": "http",
"url": "https://trustedmcp.io/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}The hosted server can't read files on your machine, so check_config needs your config pasted in as the config argument. The npx version below reads your config files locally.
Run locally with npx
Needs Node.js 18 or later.
Claude Code
claude mcp add trustedmcp -e TRUSTEDMCP_API_KEY=YOUR_KEY -- npx -y trustedmcp mcpClaude Desktop, Cursor, Windsurf (claude_desktop_config.json, ~/.cursor/mcp.json, ~/.codeium/windsurf/mcp_config.json)
{
"mcpServers": {
"trustedmcp": {
"command": "npx",
"args": ["-y", "trustedmcp", "mcp"],
"env": { "TRUSTEDMCP_API_KEY": "YOUR_KEY" }
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"trustedmcp": {
"type": "stdio",
"command": "npx",
"args": ["-y", "trustedmcp", "mcp"],
"env": { "TRUSTEDMCP_API_KEY": "YOUR_KEY" }
}
}
}Then ask: "Check my MCP config with TrustedMCP", or "What grade does @playwright/mcp get, and is there something better?"
What leaves your machine
With the hosted endpoint, whatever you pass to a tool is sent to trustedmcp.io. The rest of this section is about the npx version.
check_config reads your config file on your machine. It sends TrustedMCP only:
each server's name in your config, and
the package names (
npm:@playwright/mcp), image names (oci:ghcr.io/github/github-mcp-server) and server URLs it found, without query strings.
Environment variables, headers, tokens, other arguments and file paths stay on your machine. A server that runs a local file (node ./server.js) is not sent at all; the tool tells you it can't be looked up. The API doesn't store what it receives. The code that builds those identifiers is in src/identifiers.ts and src/config.ts.
Settings
Variable | Default | What it does |
| none | Required for tool calls. Free key from trustedmcp.io/developers, with the scopes |
|
| API base URL, for testing against another copy. |
The API
The server is a thin client for the free TrustedMCP JSON API (https://trustedmcp.io/api/v1: /servers, /servers/{slug}, /lookup, /check, /registry/{name}, /categories). Docs and terms: trustedmcp.io/developers. Where you show a grade, credit "Grades by TrustedMCP" and link to the server's page.
Develop
npm install
npm test # vitest
npm run build # tsc to dist/
TRUSTEDMCP_API_URL=http://127.0.0.1:8000/api/v1 node dist/cli.js mcpTool calls need a key even when you point TRUSTEDMCP_API_URL at a local copy.
Release (maintainers): bump version in package.json and both version fields in server.json (top level and packages[0]), npm publish, then node scripts/publish-registry.mjs to publish the same version to the official MCP Registry. That script needs the domain key for io.trustedmcp/*; it never leaves the maintainer's machine.
Use it as a library:
import { createServer, TrustedMcpApi } from 'trustedmcp';Missing a server?
If a server you use has no grade, ask for one.
License
MIT
Available Tools
4 toolscheck_configCheck an MCP configARead-onlyIdempotent
Grade every MCP server in an MCP config. With no arguments, reads the usual config files on this machine (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf). Or pass client for one app, path for one file, or config with the JSON text. The file is read locally; only package names, image names and server URLs (no query strings) are sent to TrustedMCP. Env vars, headers, tokens and file paths never leave the machine.
Inputs: path, client, config.
find_alternativesFind graded MCP serversARead-onlyIdempotent
List TrustedMCP-graded MCP servers, best grade first. Filter by category ('databases', 'browser automation'), a search term, or the minimum grade; or pass instead_of with a server name or package to get better-graded servers in its category.
Inputs: limit, query, category, min_grade, +1 more.
lookup_serverLook up an MCP serverARead-onlyIdempotent
Get an MCP server's TrustedMCP grade (A-D) by name, npm or PyPI package, Docker image, server URL, GitHub repo or launch command (e.g. 'npx -y @playwright/mcp'). Returns the four checks (login, upkeep, known bugs, connection), what to fix first and the TrustedMCP page. For servers without a grade, returns matching official MCP Registry entries.
Inputs: query (required).
registry_lookupOfficial MCP Registry entryARead-onlyIdempotent
Get an official MCP Registry entry ('io.github.owner/repo') with its packages, remotes, TrustedMCP grade if any, and reported security issues (GHSA/CVE advisories, and whether the listed version is affected). Also accepts a package name or search term and picks the best matching entry.
Inputs: name (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
check_config and find_alternatives are clearly distinct purposes, but lookup_server and registry_lookup overlap heavily: both accept a package name or search term, both return a TrustedMCP grade, and lookup_server even falls back to returning registry entries. An agent must infer 'grade-first vs registry-entry-first' intent from subtle wording rather than a clear boundary.
All four names are snake_case and readable, with three following verb_noun (lookup_server, check_config, find_alternatives). Only registry_lookup flips to noun_verb, a minor deviation that still reads sensibly.
Four tools is a tight, sensible surface for a server-grading service: single lookup, bulk config audit, discovery, and registry metadata. It is slightly lean (no way to browse all categories or compare two servers directly), but every tool earns its place.
The lifecycle is largely covered: query one server, audit a whole config, find better-graded replacements, and fetch registry/security advisories. Minor gaps exist around cross-server comparison, grade explanation/reporting, and enumerating categories, none of which blocks core agent workflows.
Maintenance
Related MCP Connectors
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Independent trust scores, tool surfaces and change history for MCP servers.
Free read-only tools for agents: agent-readiness audit, TLS/DNS/header checks, MCP search, utils.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Related MCP Servers
- AlicenseAqualityCmaintenanceSecurity scanning for MCP servers from the inside out. Provides runtime inspection, AST-based static analysis, config audit, dependency analysis, and OWASP MCP Top 10 compliance in a single MCP server.55194 npm6MIT

repo-doctorofficial
AlicenseNot gradedqualityDmaintenanceMCP server that produces scored, evidence-cited audits of public GitHub repos via tools for fetching metadata, reading files, scanning git history, and checking hygiene.MIT- AlicenseNot gradedqualityCmaintenanceEnables searching and comparing cataloged MCP servers by capability, retrieving installation snippets and trust reports, and checking a ledger of requested abilities through MCP tools.MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to inspect and diagnose their own MCP setup by exposing read-only tools that audit configured servers, report which coding agents have configs, surface misplaced or duplicated registrations, and list curated preset packs. It also powers CLI workflows for checking handshake, tool lint, and tool-surface quality scores of any stdio server.16 npmMIT