MCP
Connect Calleague to Model Context Protocol clients so an assistant can discover and call your tools.
The Model Context Protocol (MCP) is a standard way for AI assistants to discover and call external tools through a common interface. Instead of building a one-off connector for every system, a tool provider publishes its capabilities once, and any MCP-capable client can use them. This page is a short, app-level overview of how MCP fits into Calleague.
How it fits
MCP separates two roles:
- Provider — publishes a set of tools that a model can call.
- Client — discovers what a provider offers and invokes those tools on the model's behalf.
Because the interface is standardised, the same tools can be reused across different assistants, and one assistant can reach many providers at once.
Calleague and MCP
Calleague works with MCP in two complementary directions:
- Consuming — a Calleague assistant can use tools published over MCP, the same way it uses any other tool mid-conversation.
- Exposing — Calleague capabilities can be made available to MCP-capable clients so they can be discovered and invoked.
Either way, MCP is another path for an assistant to reach external capability, with the benefit of a shared, discoverable contract.
Treat an MCP connection like any other privileged integration: scope its access narrowly, keep its credentials in your own secret store, and confirm it is covered by your retention and consent settings before it touches customer data.
Related
- REST API — authentication and the call/assistant endpoints.
- Webhooks & events — receive call events in real time.