CheckMCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
CheckMCP
Vendor-neutral quality / security / context-cost audit & score for any MCP server.
One uvx/pipx command → an MCP Score /100 + causal opportunities (why the score), Lighthouse-style.
Installed from PyPI as
audit-mcp(the namecheckmcpwas already taken); the command isaudit-mcp. Brand, site and repo remain CheckMCP / checkmcp.dev.
uvx audit-mcp https://mcp.deepwiki.com/mcp
# or
pipx run audit-mcp https://mcp.context7.com/mcp --json
audit-mcp https://my-mcp.example.com/mcp --token "$TOKEN"Use it as an MCP server
audit-mcp mcp turns the auditor itself into an MCP server (stdio) exposing one tool,
audit_mcp_server — so your agent can answer "is this MCP server safe?" mid-conversation.
# Claude Code
claude mcp add audit-mcp -- uvx audit-mcp mcp// Cursor (.cursor/mcp.json) / Claude Desktop (claude_desktop_config.json)
{ "mcpServers": { "audit-mcp": { "command": "uvx", "args": ["audit-mcp", "mcp"] } } }Registry name: io.github.H129hj/checkmcp
No dependencies (stdlib only). tiktoken optional for exact token counts.
Related MCP server: mcp-audit-server
What it measures (7 pillars)
Security — OWASP MCP Top 10 (tool poisoning, hardcoded secrets, command injection), lethal-trifecta.
Tool design — sprawl/consolidation (percentile-calibrated on real servers: median ~7 tools, p95 ~42).
Schemas / desc — descriptions +
inputSchema/outputSchemacompleteness.Context-cost — tokens spent on
tools/list, paid on every request (the #1 pain of 2026).Compliance — protocol-version gap, annotations, JSON-RPC error conformance, OAuth discovery.
Reliability — single-shot today (not credited; continuous T3 monitoring on checkmcp.dev).
Coverage — the 3 primitives (tools + resources + prompts).
Hard floors: secret-in-schema → cap D, failed handshake → cap F. Every penalty is attributed: measure → mechanism → effect → Δscore.
CLI flags
flag | what |
| machine-readable report |
| SVG badge + README embed snippets |
| standalone SEO/GEO page (JSON-LD |
| add maintenance/license/provenance signal from GitHub |
| audit an OAuth-protected server |
| CI: exit 1 if MCP Score < N |
| CI: pin tool definitions; fail on regression (rug-pull) |
| CI: write a Markdown summary to |
| runtime depth via an external scanner (mcp-scan/snyk) if present |
| behavioral sandbox: actually invokes read-only tools with canary inputs to catch tool-output prompt-injection, exfiltration vectors, secret/PII leakage and context bombs (sends real traffic; CI-fails on a malicious verdict) |
GitHub Action
# .github/workflows/mcp-audit.yml
name: MCP audit
on: [push, pull_request]
jobs:
checkmcp:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: H129hj/checkmcp@v1
with:
url: https://my-mcp.example.com/mcp
min-score: "70"
baseline: .checkmcp-baseline.json # commit it → fails on rug-pullBehavioral evals (--evals)
Static analysis catches declared danger; --evals catches runtime danger by actually invoking
read-only tools with canary inputs and inspecting the responses for tool-output prompt-injection,
exfiltration vectors and secret/PII leakage (multilingual; optional callback-canary confirms exfil).
CI-fails on a malicious verdict.
Self-hosted security gateway
Beyond auditing, CheckMCP ships an in-band MCP gateway — a proxy you put between your agent and an MCP server. It inspects every call, and in active mode blocks/strips tool-poisoning & exfiltration before they reach the agent. Run it in your own infra (tool traffic never leaves your network):
docker pull ghcr.io/h129hj/checkmcp-gateway:latest # or build from source
docker run -p 8080:8080 -e GATEWAY_BACKEND_URL=https://mcp.example.com/mcp \
-e GATEWAY_MODE=active -e GATEWAY_SECRET=$(openssl rand -hex 16) \
ghcr.io/h129hj/checkmcp-gateway:latestSee GATEWAY.md for config (passive/active, OAuth backends, policy, logs).
Hosted
Full reports, public directory, live badges, continuous drift monitoring, a governance policy API and a hosted gateway at checkmcp.dev.
Honest limitations
Percentile bands come from a growing corpus (one+ registries) — widening over time.
Exact tokens with
pipx install "audit-mcp[exact-tokens]"(cl100k_base); otherwise chars/4 approximation.Pillar weights are expert priors.
python -m checkmcp.calibrate samples.jsonvalidates them against a labeled agent-success sample (per-pillar correlation + OLS-suggested weights + construct-validity R²) — supply real outcomes to close the loop.
MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.
Scores any MCP server before you trust it: free quick check, full paid report, 2-5 way compare.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables hybrid code audits using MCP tools across 12 domains, producing structured, scored, and actionable code quality reports.7 npm1MIT
- AlicenseNot gradedqualityCmaintenanceThis MCP server enables security auditing for MCP configurations and AI agents, including prompt injection testing, data flow tracing, and security policy generation.61 npmMIT
- AlicenseNot gradedqualityDmaintenanceSecurity auditor for MCP servers that enumerates tools, resources, and prompts, scans for injection patterns, classifies risk levels, and produces a scored report (0-100, grades A-F).37 PyPI2MIT
- AlicenseAqualityDmaintenanceAn MCP server that audits websites for accessibility (WCAG 2.1 AA/EAA), performance, SEO, design quality, and mobile responsiveness, providing actionable scores, grades, and prioritized fixes.6MIT