mcp-agent-guard is an MIT-licensed runtime security proxy for MCP agent tool calls. It helps developers inspect, control, and audit tool interactions in agent-based applications.
In the Security & compliance platforms space, mcp-agent-guard takes a focused approach. It focuses on securing and auditing MCP agent tool calls before they reach connected tools. mcp-agent-guard is an open-source project aimed at AI application developers. mcp-agent-guard is open source under the MIT license. It runs on the command line, and it can be self-hosted.
Behind mcp-agent-guard is mmbinumer, and it first shipped in 2026. Development happens publicly on GitHub with 30 commits in the last 90 days. Key capabilities include tool call proxying, runtime security, and audit logging. 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