> ## 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.

# Data MCP

> Query PolyAI conversation data — transcripts, metrics, and analytics — from any MCP client.

**Data MCP** is PolyAI's authenticated [MCP](https://modelcontextprotocol.io) server for conversation data. Connect an MCP client — [Claude Code](https://www.claude.com/product/claude-code), [Cursor](https://cursor.com), [Claude Desktop](https://claude.ai/download), or [Codex](https://developers.openai.com/codex/cli/) — and you can search conversations, read transcripts, and aggregate metrics in plain language, without calling the [REST API](/api-reference/introduction) directly.

## Data MCP vs Builder MCP

Both are PolyAI-hosted servers you connect **in** to. They cover different jobs and authenticate differently.

|                   | **Data MCP**                                             | **Builder MCP**                          |
| ----------------- | -------------------------------------------------------- | ---------------------------------------- |
| **What it's for** | Query conversation data: transcripts, metrics, analytics | Build, test, and deploy agents           |
| **Authenticates** | Account API key                                          | Account API key                          |
| **Endpoint path** | `/data-mcp`                                              | `/builder-mcp`                           |
| **Docs**          | This page                                                | [Builder MCP](/mcp/builder/introduction) |

<Note>
  To connect a client **out** from a live agent to a third-party server instead, see [Agent Studio MCP integrations](/mcp/agent-studio-integrations).
</Note>

## What you can do

<CardGroup cols={2}>
  <Card title="Conversation search" icon="magnifying-glass">
    Find conversations by their metrics and scores — filter and sort on quality scores, duration, and outcomes over a date range.
  </Card>

  <Card title="Transcripts" icon="file-lines">
    Read the full, turn-by-turn record of a conversation, or search across many conversations for a word or phrase with surrounding context.
  </Card>

  <Card title="Metrics catalog" icon="list-check">
    List the metrics available for an account or project — the built-in ones plus any custom metrics your projects define.
  </Card>

  <Card title="Analytics" icon="chart-line">
    Roll a metric up over time into buckets you can chart — grouped, filtered, and thresholded however you like.
  </Card>
</CardGroup>

## Get started

### 1. Get an account API key

Every request carries an API key in the `X-API-KEY` header. Data MCP uses an **account API key**, created from your account page in Agent Studio — it's scoped to the account and can query any project in it. See [Authentication](/mcp/authentication) for details.

### 2. Set your key and endpoint

Keys are region-specific — a US key doesn't work against the UK endpoint. Match the region to where your account lives. Self-serve (Studio) accounts are supported too.

| Region | Endpoint                              |
| ------ | ------------------------------------- |
| US     | `https://api.us.poly.ai/data-mcp`     |
| UK     | `https://api.uk.poly.ai/data-mcp`     |
| EU     | `https://api.eu.poly.ai/data-mcp`     |
| Studio | `https://api.studio.poly.ai/data-mcp` |

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
export POLYAI_API_KEY="your_api_key_here"
export POLYAI_DATA_MCP_URL="https://api.us.poly.ai/data-mcp"   # use your region
```

### 3. Add the server to your client

<Tabs>
  <Tab title="Claude Code">
    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    claude mcp add --transport http polyai-data "$POLYAI_DATA_MCP_URL" \
      --header "X-API-KEY: $POLYAI_API_KEY" \
      --header "Accept: application/json, text/event-stream"
    ```

    Verify with `claude mcp list`, then ask Claude to list its PolyAI data tools.
  </Tab>

  <Tab title="Cursor">
    Add to `~/.cursor/mcp.json`:

    ```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
    {
      "mcpServers": {
        "polyai-data": {
          "url": "https://api.us.poly.ai/data-mcp",
          "headers": { "X-API-KEY": "your_api_key_here" }
        }
      }
    }
    ```

    Restart Cursor, then open the MCP settings to confirm the tools loaded.
  </Tab>

  <Tab title="Claude Desktop">
    Add to your `claude_desktop_config.json`:

    ```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
    {
      "mcpServers": {
        "polyai-data": {
          "url": "https://api.us.poly.ai/data-mcp",
          "headers": { "X-API-KEY": "your_api_key_here" }
        }
      }
    }
    ```

    Restart Claude Desktop. The tools appear in the tools menu.
  </Tab>

  <Tab title="Codex">
    Add to your Codex MCP config:

    ```toml theme={"theme":{"light":"github-light","dark":"github-dark"}}
    [mcp_servers.polyai-data]
    url = "https://api.us.poly.ai/data-mcp"
    headers = { "X-API-KEY" = "your_api_key_here" }
    ```
  </Tab>
</Tabs>

<Tip>
  Working across regions? Add the server once per region under distinct names (e.g. `polyai-data-us`, `polyai-data-uk`, `polyai-data-eu`), each with that region's key.
</Tip>

## Capabilities

Data MCP exposes 5 tools — conversation search, transcript search, single-conversation fetch, a metrics catalog, and metric aggregation. See [Capabilities](/mcp/data/capabilities) for each tool and its parameters.

<Card title="Browse the tools" icon="list-check" href="/mcp/data/capabilities">
  Every Data MCP tool, grouped by what it does, with its parameters.
</Card>