mcp-airlock

Purpose: Controlling and auditing MCP tool access with policy enforcement, dry runs, human confirmation, and tracing.

Inferred · not functionally tested

Audience: developers building or operating MCP servers and AI agent systems

Inferred · not functionally tested

Functions: monitoring

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · 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, api_only

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 security & guardrails space, mcp-airlock takes a focused approach. Inferred · not functionally tested: It focuses on controlling and auditing MCP tool access with policy enforcement, dry runs, human confirmation, and tracing. Inferred · not functionally tested: mcp-airlock is an open-source project aimed at developers building or operating MCP servers and AI agent systems. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the command line and API, and it can be self-hosted.

It is developed by Shalimov04, and it first shipped in 2026. The project is developed in the open on GitHub with 23 stars and 7 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include policy enforcement, dry-run mode, and human confirmation. Inferred · not functionally tested: Catalogued interfaces include an MCP server.

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