domains / families / security / auditing-mcp-servers-for-tool-poisoning

auditing-mcp-servers-for-tool-poisoning

separate

Audit MCP servers for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure using Invariant Labs' mcp-scan for static/runtime scanning plus manual SSRF/auth checks and description pinning. Use before adding a new MCP server to an agent stack, when reviewing an internal MCP server, detecting rug pulls, or investigating an agent's unexpected tool-driven behavior.

When to use

• Before adding a new MCP server to an agent stack (Claude Desktop, Cursor, VS Code, Windsurf, custom agents).
• During a security review of an internally developed MCP server.
• When validating that approved tools have not silently changed (rug-pull detection).
• As a CI/CD gate that scans MCP configs and SKILL/tool definitions on every change.
• During incident response when an agent took unexpected actions consistent with a poisoned tool.

When not to use

• Probing third-party MCP endpoints without permission
• Loading unaudited MCP servers into privileged agents

Skill page

Source