mcp-airlock

Purpose: Controlling and auditing MCP tool access without embedding governance logic into each MCP client or server.

Inferred · not functionally tested

Audience: developers and platform security teams building MCP-based 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: Open Source · platforms: WEB · deployment: browser, self_hosted, cli, api_only

Constraint provenance is unknown; confirm requirements with the publisher.

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

mcp-airlock sits in PulseGate's AI security & guardrails category. Inferred · not functionally tested: It focuses on controlling and auditing MCP tool access without embedding governance logic into each MCP client or server. Inferred · not functionally tested: It is built as an open-source project for developers and platform security teams building MCP-based systems. Basis unknown · not verified: mcp-airlock is open source under the Open Source license. Basis unknown · not verified: mcp-airlock is available on the web, the command line, and API, and it can be self-hosted.

It is developed by Shalimov04. Inferred · not functionally tested: Among its 6 catalogued features are 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.