Tool Poisoning And Malicious Function Detection

via “live-mcp-server-tool-poisoning-audit”

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

Unique: Performs runtime introspection and behavioral testing of live MCP server tools, comparing actual tool responses against expected baselines to detect poisoning attacks that modify tool behavior without changing tool schemas

vs others: More effective than static configuration validation because it tests actual tool behavior at runtime, catching poisoning attacks that only manifest during execution rather than in configuration files

** - A comprehensive security scanner for Model Context Protocol (MCP) servers that detects vulnerabilities and security issues in your MCP server implementations.

Unique: Analyzes MCP-specific tool definitions and function implementations to detect poisoning attacks targeting the tool interface, using data flow analysis to identify suspicious exfiltration or command execution patterns unique to MCP protocol

vs others: MCP-specific tool poisoning detection versus generic code analysis tools that lack understanding of MCP tool semantics and attack vectors

via “model poisoning detection”

via “model poisoning detection”