mcp-agent-guard

Purpose: Securing and auditing MCP agent tool calls before they reach connected tools.

Inferred · not functionally tested

Audience: AI application developers

Inferred · not functionally tested

Functions: monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

In the AI & LLM security space, mcp-agent-guard takes a focused approach. Inferred · not functionally tested: It focuses on securing and auditing MCP agent tool calls before they reach connected tools. Inferred · not functionally tested: mcp-agent-guard is an open-source project aimed at AI application developers. Basis unknown · not verified: mcp-agent-guard is open source under the MIT license. Basis unknown · not verified: 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. Inferred · not functionally tested: Key capabilities include tool call proxying, runtime security, and audit logging. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.