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

# Model Context Protocol (MCP)

> Connect AI agents to Dealroom data through the Dealroom MCP server. Install in Cursor, Claude Desktop, or any MCP-compatible client.

The Dealroom MCP server exposes Dealroom's data — companies, investors,
funding rounds, founders, ecosystems, news — as Model Context Protocol tools so
AI agents can query it conversationally without you writing API client code.

## Server endpoint

```text theme={null}
https://mcp.dealroom.co/mcp
```

The server speaks the standard MCP JSON-RPC over HTTP and authenticates with
the same Auth0 OAuth2 flow as the REST API.

## One-click install

Click the **Install in Cursor** action in the top-right of any docs page to
register the Dealroom MCP server with your local Cursor installation. The
button is wired to the `cursor://` deeplink protocol and configures the
server endpoint for you.

## Manual install (Claude Desktop, Cline, other clients)

Add the following to your client's MCP config:

```json theme={null}
{
  "mcpServers": {
    "dealroom": {
      "url": "https://mcp.dealroom.co/mcp"
    }
  }
}
```

Your client will prompt for Auth0 authentication on first connect.

## What you can ask the agent

The MCP server exposes the same resource shapes as the REST API. Sample
prompts:

* "Find the top 10 fintech startups in the Netherlands by total funding."
* "Compare Stripe's portfolio to Adyen's."
* "Show me unicorn rounds in 2025 with revenue over \$100M."

Behind the scenes the agent calls the same `/api/data/entities`, `/api/analytics/aggregate`,
and `/api/analytics/funding-analytics` endpoints documented in the
[API Reference](/api-reference) — the MCP layer just translates natural
language into structured queries.
