veil-mcp is an open-source CLI firewall for Model Context Protocol (MCP) tool calls, descriptors, and results. It helps AI infrastructure engineers secure and filter agent workflows using MCP integrations.
In the AI & LLM security space, veil-mcp takes a focused approach. It focuses on securing and filtering Model Context Protocol (MCP) tool calls and results for AI agent workflows. veil-mcp is an open-source project aimed at AI infrastructure engineers. The project is open source (MIT). It ships for the web and the command line, and it can be self-hosted.
It is developed by Atomics-hub, and it first shipped in 2026. Development happens publicly on GitHub with 10 commits in the last 90 days. Among its 5 catalogued features are MCP firewall, tool call filtering, and descriptor protection. 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