Skip to main content
The Model Context Protocol (MCP) is an open standard for connecting AI systems to tools. PolyAI works with MCP in two directions — and it’s worth being clear which one you want before you start, because they solve opposite problems.

Two directions

Builder MCP

Build agents. Point an MCP client — Cursor, Claude Code, Claude Desktop, Codex — at PolyAI’s authenticated MCP server and build, test, and deploy your agents from your IDE. This is PolyAI’s own hosted MCP.

Agent Studio MCP integrations

Consume external tools. Add a third-party MCP server inside Agent Studio so your live agent can call its tools during conversations. This is your agent acting as a client of someone else’s server.
You want to…UseDirection
Build and manage PolyAI agents from an IDE or AI coding toolBuilder MCPClient → PolyAI
Let your live agent look up data or trigger actions in another systemAgent Studio MCP integrationsPolyAI → external server
The rest of this section documents PolyAI’s authenticated MCP — the Builder MCP and any servers we add later. For the connect-out direction, see Agent Studio MCP integrations.

Get connected

1

Authenticate

Create a workspace-scoped API key and configure your client’s auth. See Authentication.
2

Connect a client

Add the server to Cursor, Claude Code, Claude Desktop, or Codex with a single command. See Quickstart.
3

Build

Use the Builder MCP to create, test, and deploy agents conversationally.

MCPs we offer

Builder MCP

Build, test, and deploy PolyAI agents — agents, data, and alerts as tools.
Last modified on July 7, 2026