mcp-audits

Purpose: Auditing and assessing security risks of permissions on Model Context Protocol (MCP) servers.

Inferred · not functionally tested

Audience: security engineers and AI infrastructure operators

Inferred · not functionally tested

Functions: monitoring, 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-audits is an AI & LLM security project. Inferred · not functionally tested: It focuses on auditing and assessing security risks of permissions on Model Context Protocol (MCP) servers. Inferred · not functionally tested: It is built as an open-source project for security engineers and AI infrastructure operators. Basis unknown · not verified: mcp-audits is open source under the MIT license. Basis unknown · not verified: mcp-audits is available on the command line, and it can be self-hosted.

It is developed by saagpatel, and it first shipped in 2026. Development happens publicly on GitHub with 210 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include permission auditing, risk scoring, and MCP server scanning. Basis unknown · not verified: Catalogued interfaces include an MCP server.

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