← Index

io.github.andrasfe/vulnicheck

io.github.andrasfe/vulnicheck·v0.1.0·Security

HTTP MCP Server for comprehensive Python vulnerability scanning and security analysis.

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
NVD_API_KEY
secret

API key for NIST National Vulnerability Database (increases rate limit from 5 to 50 requests per 30 seconds)

GITHUB_TOKEN
secret

GitHub token for Advisory Database access (increases rate limit to 5000 requests per hour)

OPENAI_API_KEY
secret

OpenAI API key for LLM-based risk assessment in MCP passthrough operations

ANTHROPIC_API_KEY
secret

Anthropic API key for LLM-based risk assessment (alternative to OpenAI)

MCP_PORT

Port for MCP HTTP server (default: 3000)

CACHE_TTL

Cache time-to-live in seconds for vulnerability data (default: 900)

VULNICHECK_HTTP_ONLY

Enable HTTP-only mode with MCP client delegation (true/false, default: auto-detect)

MCP quality score · maturity, not trust · methodology
freshness
7
completeness
10
installability
25
documentation
15
stability
5
Alternatives in Security