Skip to main content
Corvic exposes its capabilities through the Model Context Protocol (MCP) — an open standard that lets AI systems and applications consume tools and data in a uniform way. With MCP you can call Corvic from your own code, notebooks, agent frameworks, or backend services.

​
Two levels of access

Use Agent MCP when you want grounded answers from a configured agent. Use Room MCP when you want the room itself — its data, pipelines, memories, lenses, and agents.

​
Getting your credentials

Every MCP request needs an endpoint URL and an access token (sent as a Bearer token):
  • Agent MCP — open your agent’s Integration & Sharing → Integration tab to copy its MCP URL and Access Token. See Agents.
  • Room MCP — open the room’s MCP Playground to copy the MCP endpoint and mint an access token with a chosen expiry. The Playground also lets you call every tool live and see the exact requests and raw responses an MCP client would send and receive.
Treat access tokens like passwords. Don’t commit them to source control — load them from environment variables or a secrets manager.

​
Connect from any platform

Both levels work with any MCP-compatible client — Claude, Cursor, agent frameworks like OpenAI, CrewAI, or LangChain, or your own backend services. Point the client at the endpoint with your Bearer token, list the tools, and call them.

Agent MCP

Tools for talking to a deployed agent.

Room MCP

The full tool surface: pipelines, memories, lenses, agents, and data access.

Connect External Services

The other direction — services into Corvic.