Skip to main content
Glama

Airlock MCP

Airlock MCP is the public connector front door for AI agents. Airlock Smith is the guided spec-building mode inside that experience.

Install

npx @airlock/mcp install

Today this package is a small installer and MCP launcher. For Codex, install registers a local stdio server with:

codex mcp add airlock -- npx -y @airlock/mcp server

The server exposes bootstrap guidance that points the user to the Codex-first Airlock Smith workflow and the public tool repo:

https://github.com/reunionstudio/airlock-smith

This install shape uses Node because npx runs npm package binaries. MCP itself does not require Node. Once Airlock MCP does real operational work, the production server should likely be Rust with rmcp: single binary, predictable memory and latency, typed tool contracts, and no Node/Python runtime for the long-running process. The npm package can remain the friendly installer.

For stdio MCP, stdout is protocol-only. Logs and diagnostics must go to stderr.

Related MCP server: Foundry MCP

Test

npm test

The smoke test verifies install dry-run output and the stdio MCP handshake for initialize, tools/list, prompts/list, and resources/list.

The intended user flow is:

  1. Run npx @airlock/mcp install once for the agent environment.

  2. Open Codex.

  3. Create a blank project repo named for the org or project, such as home-specs.

  4. Ask Codex to use Airlock Smith from the public repo.

  5. Let Codex bootstrap the project and welcome the user before creating the first workspace.

The first workspace should not be created automatically. Airlock Smith should offer OODA brainstorming, a known-process draft, or a shared posts feedback loop.

F
license - not found
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/reunionstudio/airlock-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server