MCP-Vetting
This server lets you vet MCP servers from remote or local sources and generate harness-specific MCP configs, returning evidence-backed trust verdicts.
Vet remote targets:
vet_serveraccepts npm:pkg, pypi:pkg, gh:owner/repo, or bare npm names, with optional strict mode.Vet local directories:
vet_directoryscans a local MCP server source directory offline, with optional strict mode.Get cached verdicts:
get_verdictreturns a cached verdict if fresh, otherwise re-vets the target.List scanners:
list_scannersshows the static scanners available (ssrf, exec, secrets, auth, provenance, deps).List harnesses:
list_harnessesshows supported config adapters (generic, claude-code, cursor, vscode, hermes).Generate configs:
get_configemits a paste-ready MCP server config block for a chosen harness, with custom command, args, env, and server name.
mcp-vet
A trust-scan framework for MCP servers: evidence-backed verdicts before you install — usable from any harness.
uvx --from mcp-vetting mcp-vet @modelcontextprotocol/server-fetch # one command
uvx --from mcp-vetting mcp-vet ./my-server --harness hermes # verdict + config for YOUR harness
uvx --from mcp-vetting mcp-vet pypi:fastmcp --json --gate # machine-readable, CI-friendlyVerdicts: SAFE_TO_INSTALL · REVIEW_BEFORE_INSTALL · DO_NOT_INSTALL — every finding carries file:line and plain-English evidence. A verdict is a gate for humans, never a black box.
The flow
Vet any target: npm / PyPI / GitHub / local directory.
Read the verdict + findings (evidence, not vibes).
Configure: pick your harness, paste the emitted config block.
Gate it in CI with
--gate(exit 1 on DO_NOT_INSTALL).
Related MCP server: MCPskills
Three surfaces, one engine
Surface | Use |
Library |
|
CLI |
|
MCP server |
|
Targets
npm:pkg npm registry + tarball (bare names default to npm)
pypi:pkg PyPI JSON + sdist/wheel
gh:owner/repo GitHub metadata + source
./path local source directory (offline)
Bare names that fail to resolve on npm (e.g. PyPI-only servers like
`mcp-server-time`) automatically fall back to PyPI before reporting failure.Harness adapters (any harness, paste-ready)
--harness emits the exact config block for your tool:
harness | output |
| universal |
|
|
|
|
|
|
|
|
--harness all prints every adapter. Programmatic: config_for(harness, ServerSpec(...)).
Policy (calibrated defaults, --strict to disable)
Static analysis must not cry wolf. Defaults, learned by vetting the real ecosystem:
Examples/tests/docs are informational —
examples/,tests/,docs/code can't block a package on its own (strict restores raw findings).Fake secrets don't count —
sk-test-…,example,xxxxliterals are placeholders, not exfiltration.Trusted-host auth is normal — credentials sent to a host named in the file (constant or literal) is client auth; HIGH only when the destination host appears nowhere in the code.
Host interpolation → REVIEW —
https://${host}/…is a strong signal, but static analysis can't prove the host is user-controlled; a human decides. Strict mode blocks on it.
JSON schema (stable)
{
"target": "npm:some-server", "kind": "npm", "version": "1.2.3",
"verdict": {
"level": "REVIEW_BEFORE_INSTALL",
"summary": "3 finding(s); 0 high, 1 medium.",
"findings": [
{"scanner": "ssrf", "severity": "medium", "message": "...",
"file": "dist/index.js", "line": 41, "evidence": "fetch(url)"}
]
},
"provenance": {"version": "1.2.3", "license": "MIT",
"source_url": "git+https://...", "source": "npm"},
"files_scanned": 214, "duration_s": 1.7
}Scanners
ssrf · exec · secrets · auth · provenance · deps — static,
local-first (no telemetry, no cloud round-trips; the cache is a local SQLite
file under ~/.cache/mcp-vet).
Verification
python3 -m unittest discover -s tests # 48 checks: golden corpus is the quality barThe golden corpus is the contract: known-good fixtures must never carry HIGH
findings; malicious fixtures must always block. The ecosystem scan
(scripts/ecosystem_scan.py) keeps the tool honest against real packages.
Honest limits
Static analysis has false positives and negatives. A verdict is a gate for humans, not a replacement for them — read the evidence. Sandboxed execution, egress audit-trail, and live CVE lookups are planned for v2.
Available Tools
6 toolsget_configA
Emit the ready-to-paste MCP config block for a harness (generic|claude-code|cursor|vscode|hermes).
Inputs: name (required), harness (required), env, args, +1 more. Returns: object
get_verdictA
Return the cached verdict for a target if fresh, else vet it now.
Inputs: target (required). Returns: object
list_harnessesC
Harnesses with ready-to-paste config adapters.
Inputs: no named parameters. Returns: result
list_scannersC
The static scanners this framework runs.
Inputs: no named parameters. Returns: result
vet_directoryC
Vet a local MCP server source directory (offline). Returns the VetResult dict.
Inputs: path (required), strict. Returns: object
vet_serverA
Vet a remote MCP server (npm:pkg, pypi:pkg, gh:owner/repo, or bare npm name). Returns the VetResult dict: verdict level/summary/findings, provenance, files scanned.
Inputs: target (required), strict. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: vetting remote vs local, retrieving cached verdicts, listing scanners, listing harnesses, and generating configs. No two tools overlap in what they do, and the descriptions reinforce their unique roles.
All tools follow a consistent verb_noun snake_case pattern: vet_server, vet_directory, get_verdict, list_scanners, list_harnesses, get_config. The verbs (vet, get, list) are descriptive and uniform.
With 6 tools, the set is well-scoped for a vetting framework, covering both operational actions and informational queries. There is no bloat or redundancy.
The tool surface covers the core lifecycle: vetting remote and local servers, retrieving cached results, enumerating available scanners and harnesses, and generating configuration. No obvious gaps hinder a user from completing a vetting workflow.
Maintenance
Related MCP Connectors
Trust verification for MCP servers. Check scores, scan for security issues, search 4,200+ servers.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Look up independent trust ratings and security, maintenance, and adoption evidence for MCP servers.
Independent trust scores, tool surfaces and change history for MCP servers.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceScans MCP servers for prompt injection, supply chain attacks, excessive permissions, and code execution risks. Includes an offline blacklist that catches known-compromised packages like LiteLLM 1.82.7/1.82.8 and Trivy with zero latency.19MIT
- AlicenseAqualityCmaintenancePre-install trust scoring & safety scanning for MCP servers, AI skills & npm packages — 15 signals incl. OSV/KEV/EPSS vuln intel and an auto-gate go/no-go.9191 npm1MIT
- AlicenseNot gradedqualityDmaintenanceScans MCP servers for security vulnerabilities, prompt injection, and tool poisoning, providing risk scores and protection.4MIT
- FlicenseNot gradedqualityDmaintenanceEnables users to search and audit MCP servers by quality metrics such as installs, security, and activity, helping them find trustworthy servers and avoid ones with no installs.-