Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
mcp-security-audit
Security auditor for MCP servers. Connects to any MCP server, enumerates its tools/resources/prompts, scans for injection patterns, classifies risk levels, and produces a scored report (0-100, grades A-F).
Works as a CLI tool (mcp-audit) or as an MCP server itself (mcp-security-audit).
Why it matters: there are now 16,000+ MCP servers in the public ecosystem — and almost none have been security-audited. Each one runs with tool access to a shell, filesystem, or network, and a single injection-laden tool description can hijack the agent that loads it. This finds the holes before an attacker does.
Want a professional audit report? We found 20 vulnerabilities in Microsoft's MCP servers. Get the same analysis for your server — $29 single audit.
Install
pip install mcp-security-auditCLI Usage
Text report
mcp-audit scan --server "python -m my_mcp_server"JSON report
mcp-audit scan-json --server "python -m my_mcp_server" --output report.jsonWith live injection tests
mcp-audit scan --server "python -m my_mcp_server" --live-testsCI/CD
Exit code 0 for grade A/B, 1 for C/D/F:
mcp-audit scan --server "uvx some-server" || echo "Security audit failed"MCP Server Mode
Use as an MCP server so AI assistants can audit other servers:
Claude Code
claude mcp add mcp-security-audit -- uvx mcp-security-auditManual
{
"mcpServers": {
"mcp-security-audit": {
"command": "uvx",
"args": ["mcp-security-audit"]
}
}
}Tools exposed
| Tool | What it does |
|---|---|
audit_scan | Full security audit with text report |
audit_quick_scan | Quick scan — score, grade, top findings |
audit_classify | Classify a single tool's risk level |
audit_check_text | Scan text for injection patterns |
What It Checks
- Tool risk classification — categorizes every tool as SHELL / FILE / DATABASE / NETWORK / SAFE
- Injection pattern scanning — scans tool and prompt descriptions for 75 injection patterns across 9 categories
- Resource URI analysis — flags sensitive paths (.env, .ssh, credentials, etc.)
- High-risk ratio — warns if >50% of tools are FILE or SHELL level
- Undocumented tools — flags tools missing descriptions
- Attack surface — warns on 20+ tools (large) or 50+ (very large)
- Live injection tests (opt-in) — sends payloads to string-parameter tools
Scoring
Starts at 100, deducts per finding:
| Severity | Deduction |
|---|---|
| CRITICAL | -25 |
| HIGH | -15 |
| MEDIUM | -8 |
| LOW | -3 |
Bonus: +1 per documented tool (max +5).
Grades: A (90+), B (75+), C (60+), D (40+), F (<40)
Example Output
============================================================
MCP SECURITY AUDIT REPORT
============================================================
Server: python -m agent_safety_mcp.server
Tools: 13
Score: 92/100 (Grade A)
------------------------------------------------------------
TOOL CLASSIFICATION
------------------------------------------------------------
Tool Risk Matched
cost_guard_configure SAFE -
cost_guard_status SAFE -
injection_scan SAFE -
trace_save FILE !!save, file
...Dependencies
- mcp — MCP protocol SDK
- ai-injection-guard — 75 prompt injection detection patterns across 9 categories
Part of the LuciferForge AI Agent Infrastructure Stack.
License
MIT