mcp-panther and mcp-audit

These are complementary tools: Panther provides detection and investigation capabilities for security incidents, while mcp-audit performs pre-incident reconnaissance by scanning MCP configurations for vulnerabilities and exposed resources that Panther would then monitor.

mcp-panther
60
Established
mcp-audit
50
Established
Maintenance 10/25
Adoption 14/25
Maturity 18/25
Community 18/25
Maintenance 10/25
Adoption 10/25
Maturity 9/25
Community 21/25
Stars: 41
Forks: 16
Downloads: 862
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 143
Forks: 35
Downloads: —
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No Package No Dependents

About mcp-panther

panther-labs/mcp-panther

Write detections, investigate alerts, and query logs from your favorite AI agents

Implements the Model Context Protocol (MCP) to expose Panther's detection, alerting, and data lake capabilities as AI agent tools—enabling natural language SQL queries against security logs, AI-powered alert triage with intelligent recommendations, and detection authoring directly from IDE-integrated agents. Provides 50+ specialized tools covering alert management (bulk operations, comments, status updates), data lake schema exploration and querying, detection lifecycle management across rules/policies, and operational metrics and access controls.

About mcp-audit

apisec-inc/mcp-audit

See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate AI-BOMs for compliance.

Performs static analysis of MCP configuration files across development tools (Claude Desktop, Cursor, VS Code, Windsurf, Zed) and GitHub repositories, using pattern matching to detect 25+ secret types and mapping findings to OWASP LLM Top 10 (2025). Exports results in multiple formats (JSON, CycloneDX AI-BOM, SARIF, CSV) for CI/CD integration and compliance workflows, with a browser-based GitHub scanner and local CLI tool that scans MCP configs without telemetry or network transmission.

Scores updated daily from GitHub, PyPI, and npm data. How scores work