> ## Documentation Index
> Fetch the complete documentation index at: https://docs.poly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP

> PolyAI's authenticated MCP servers let any MCP client build agents and query their data. Learn the two directions MCP works and which one you need.

The [Model Context Protocol](https://modelcontextprotocol.io/) (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

> [card] [PolyAI's MCP servers](https://docs.poly.ai/mcp/quickstart.md)
>
> **Connect a client in.** Point an MCP client — Cursor, Claude Code, Claude Desktop, Codex — at one of PolyAI's authenticated, hosted MCP servers to build agents or query their data from your IDE. Your tool acts as a client of PolyAI's server.

> [card] [Agent Studio MCP integrations](https://docs.poly.ai/mcp/agent-studio-integrations.md)
>
> **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… | Use | Direction |
| - | - | - |
| Build and manage PolyAI agents from an IDE or AI coding tool | [Builder MCP](https://docs.poly.ai/mcp/builder/introduction.md) | Client → PolyAI |
| Query conversation data — transcripts, metrics, analytics — from a client | [Data MCP](https://docs.poly.ai/mcp/data/introduction.md) | Client → PolyAI |
| Let your live agent look up data or trigger actions in another system | [Agent Studio MCP integrations](https://docs.poly.ai/mcp/agent-studio-integrations.md) | PolyAI → external server |

> [!NOTE]
>
> The rest of this section documents **PolyAI's authenticated MCP servers** — the ones you connect a client to. For the connect-out direction, see [Agent Studio MCP integrations](https://docs.poly.ai/mcp/agent-studio-integrations.md).

## PolyAI's MCP servers

PolyAI hosts two authenticated MCP servers. They cover different jobs, but connect the same way — both use the streamable HTTP transport, run in the same regions, and take the same **account API key** in the `X-API-KEY` header.

> [card] [Builder MCP](https://docs.poly.ai/mcp/builder/introduction.md)
>
> Build, test, and deploy PolyAI agents — agents, data, and alerts as tools.

> [card] [Data MCP](https://docs.poly.ai/mcp/data/introduction.md)
>
> Query conversation data — search conversations, read transcripts, aggregate metrics.

| | **Builder MCP** | **Data MCP** |
| - | - | - |
| **What it's for** | Build, test, and deploy agents | Query conversations, transcripts, and metrics |
| **Authenticates** | Account API key | Account API key |
| **Endpoint path** | `/builder-mcp` | `/data-mcp` |
| **Regions** | US, UK, EU, Studio | US, UK, EU, Studio |

## Get connected

**1. Authenticate**

Create the API key your server needs and configure your client's auth. See [Authentication](https://docs.poly.ai/mcp/authentication.md).

**2. Connect a client**

Add the server to Cursor, Claude Code, Claude Desktop, or Codex with a single command. See [Quickstart](https://docs.poly.ai/mcp/quickstart.md).

**3. Build or query**

Use the [Builder MCP](https://docs.poly.ai/mcp/builder/introduction.md) to create, test, and deploy agents, or the [Data MCP](https://docs.poly.ai/mcp/data/introduction.md) to query conversation data — all conversationally.
