mcp-triage is an open-source command-line security scanner for Model Context Protocol servers. It helps developers and security teams analyze MCP server implementations for vulnerabilities and unsafe configurations in AI agent workflows.
In the AI & LLM security space, mcp-triage takes a focused approach. It focuses on scanning MCP servers for security issues before they are used in AI agent workflows. mcp-triage is an open-source project aimed at developers and security engineers building MCP integrations. The project is open source (MIT). It runs on the command line, and it can be self-hosted.
Behind mcp-triage is YashkantG, and it first shipped in 2026. The project is developed in the open on GitHub with 16 commits in the last 90 days. Key capabilities include MCP scanning, static analysis, and security checks. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do