Skip to main content
MCP (Model Context Protocol) is the emerging standard for how AI systems call tools. Airia sits on both sides of that standard at once: it’s a client that connects your agents to thousands of catalogue and custom MCP servers, and it’s a server that exposes those same connections to any external MCP-compatible client your team already uses. In practice, that means one governed place to approve apps, manage credentials, and control exactly which tools an AI can call, whether the AI asking is an agent built inside Airia or a coding assistant like Cursor or Claude Code running on someone’s laptop.

​
Two Ways to Connect

Every integration in Airia is built from the same three ingredients: an app, its credentials, and the specific tools you expose. What changes is scope and where it’s used.
DeploymentGateway
ScopeOne app, for use inside Airia agentsOne or more apps, bundled behind a single endpoint
Used byAn AI Model step inside an Airia agentExternal MCP clients (Cursor, Claude Code, Claude Desktop, etc.), or an agent’s tool section
VisibilityScoped to a project, or all projectsPersonal (just you) or Tenant (your whole org)
Who can create oneAny project member with accessPlatform Admin or Security Admin
See Deployments vs. Gateways for the full comparison, and Gateway/Deployment Creation for how to build either one.

​
Built-In Governance

Because every connection, whether it’s feeding an internal agent or an external client, passes through the same layer, a few things come for free:
  • A single approval gate. Admins decide which of Airia’s 1,200+ catalogue servers (plus any custom ones) are usable at all, before anyone can add them to a Gateway or Deployment. See Server Management.
  • Prompt injection screening. Every tool’s name and description is scanned for hidden prompt injection attempts before it’s exposed. See Tool Scanning.
  • Full activity visibility. Every tool call, whether it succeeded, was denied, or errored, is logged and searchable. See MCP Monitoring.
  • Context-efficient scaling. Radar lets a Gateway with hundreds of tools stay lightweight by letting agents search for what they need instead of loading every tool definition up front.
  • Org-specific know-how. The Instructions Tool attaches your team’s own conventions, naming, and workflows to a Gateway or Deployment, so agents use your tools the way your team actually works.

​
What’s in This Section

GroupWhat You’ll Find
Admin ControlsApproving servers, creating and editing Gateways and Deployments, credentials, tool scanning, Radar, Instructions, custom servers, and SpecLink
End User UsageConnecting a Gateway to Cursor, Claude Code, or Claude, and recovering a broken credential
Popular MCP ServersSetup guides for commonly connected servers like Microsoft Graph, Airtable, Snowflake, Jira, Confluence, Box, and Brave Search

​
Getting Started

If you’re an admin:
  1. Approve the servers your organization is allowed to use.
  2. Create a Gateway or Deployment and connect credentials for the apps you need.
  3. Share the Gateway with your team, or attach the Deployment to an agent.
  4. Keep an eye on usage with MCP Monitoring.
If you’re an end user:
  1. Connect a Gateway to Cursor, Claude Desktop, or Claude Code.
  2. Add a Deployment to an agent if you’re building agents rather than using an external client.
  3. If a connection ever stops working, Credential Recovery gets you back up in a click.