mcp-guard-audit

Purpose: Auditing MCP servers and AI agents for tool poisoning, prompt injection, risky tools, and leaked secrets.

Inferred · not functionally tested

Audience: AI security engineers and developers building MCP servers or agents

Inferred · not functionally tested

Functions: data_extraction

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.

mcp-guard-audit is an AI & LLM security project. Inferred · not functionally tested: It focuses on auditing MCP servers and AI agents for tool poisoning, prompt injection, risky tools, and leaked secrets. Inferred · not functionally tested: It is built as an open-source project for AI security engineers and developers building MCP servers or agents. Basis unknown · not verified: mcp-guard-audit is open source under the MIT license. Basis unknown · not verified: It ships for the command line, and it can be self-hosted.

ianewsfr-a11y builds and maintains mcp-guard-audit, and it first shipped in 2026. Development happens publicly on GitHub with 9 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include MCP server auditing, AI agent auditing, and tool risk detection. Basis unknown · not verified: Catalogued interfaces include an MCP server.

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