io.github.andrasfe/vulnicheck
HTTP MCP Server for comprehensive Python vulnerability scanning and security analysis.
{
"mcpServers": {
"vulnicheck": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"docker.io/andrasfe/vulnicheck:main"
],
"env": {
"NVD_API_KEY": "<your-nvd_api_key>",
"GITHUB_TOKEN": "<your-github_token>",
"OPENAI_API_KEY": "<your-openai_api_key>",
"ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
"MCP_PORT": "<mcp_port>",
"CACHE_TTL": "<cache_ttl>",
"VULNICHECK_HTTP_ONLY": "<vulnicheck_http_only>"
}
}
}
}NVD_API_KEYAPI key for NIST National Vulnerability Database (increases rate limit from 5 to 50 requests per 30 seconds)
GITHUB_TOKENGitHub token for Advisory Database access (increases rate limit to 5000 requests per hour)
OPENAI_API_KEYOpenAI API key for LLM-based risk assessment in MCP passthrough operations
ANTHROPIC_API_KEYAnthropic API key for LLM-based risk assessment (alternative to OpenAI)
MCP_PORTPort for MCP HTTP server (default: 3000)
CACHE_TTLCache time-to-live in seconds for vulnerability data (default: 900)
VULNICHECK_HTTP_ONLYEnable HTTP-only mode with MCP client delegation (true/false, default: auto-detect)
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.
Provide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…
Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails