Introduction

Airlock is a secure gateway that connects AI agents to your APIs. It provides:

• Pre-built Integrations: Connect to GitHub, Linear, Notion, Google Calendar, and 25+ other services instantly
• Custom API Support: Bring any API with an OpenAPI specification
• MCP Protocol Support: Native integration with Claude Desktop, Claude Code, Augment, and other MCP clients
• Approval Workflows: Human-in-the-loop controls for sensitive operations
• Per-User Authentication: Each user connects with their own credentials
• Policy Engine: Fine-grained access control for each API operation
• Security Monitoring: Automated anomaly detection and auto-blocking

How It Works

AI Agent ──── MCP Protocol ────→ Airlock ────→ Your API / Service
                                    │
                                    ├── Policy Evaluation
                                    ├── Approval Workflow (if required)
                                    ├── Security Monitoring
                                    └── Audit Logging

1. Create a Server: Pick a pre-built integration or upload an OpenAPI specification
2. Set Policies: Define which operations are allowed or require approval
3. Connect Users: Each user authenticates via MCP OAuth and connects their own credentials
4. AI Calls API: The AI agent calls tools, Airlock evaluates policies and routes accordingly

Key Concepts

Servers

A server in Airlock represents an API or service you want to expose to AI agents. Airlock supports several server types:

Type	Description
Pre-built Integration	Connect to services like GitHub, Linear, Notion, etc. with minimal configuration
Custom OpenAPI	Bring any REST API with an OpenAPI specification
Knowledge Graph	Memgraph-backed knowledge graph for storing entities and relationships
Database	Per-organization PostgreSQL database for structured data access

Policies

Policies determine what happens when an AI agent tries to call an API operation:

• ALLOW: The operation executes immediately
• REQUIRE_APPROVAL: The operation waits for human approval before executing

By default, new tools are set to ALLOW. You can toggle any tool to require approval from the server detail page.

Approval Workflows

When a policy requires approval:

1. Airlock creates a pending request
2. Designated approvers are notified via email
3. Approvers can approve or reject from the web UI
4. The AI agent receives the result and can proceed or handle the rejection

Organization-Wide Access

In addition to per-server MCP endpoints, Airlock provides an organization-wide MCP endpoint that lets agents discover and use tools across all your servers. Agents use meta-tools (list_services, search_tools, describe_tools, execute_tool, activate_skill) to navigate available APIs dynamically.

Security

Airlock monitors API usage for anomalous patterns and can automatically block suspicious activity. Security blocks are visible in the Control Room and can be managed by admins.

API Endpoints

Airlock exposes two transport options for AI agent communication:

Transport	URL	Purpose
HTTP	mcp.air-lock.ai	Primary MCP endpoint (stateless, used by most clients)
WebSocket	ws.air-lock.ai	Real-time bidirectional MCP with push notifications

Next Steps

• Quickstart - Get up and running in 5 minutes