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

# MCP Overview

> ClosedLoop AI's MCP brings product intelligence into Claude Code, Cursor, and any MCP-compatible AI tool: query insights without leaving your editor.

ClosedLoop AI is built for the agentic stack. Connect Claude Code, Cursor, or any MCP-compatible AI tool to your workspace, and your AI dev agent can query product intelligence, explore revenue-scored opportunities, and trace insights back to real customer quotes, all without leaving your IDE.

## Setup

<Steps>
  <Step title="Add the MCP">
    <Tabs>
      <Tab title="Claude Code">
        ```bash theme={null}
        # US workspace
        claude mcp add --transport http closedloop-ai https://mcp.closedloop.sh

        # EU workspace
        claude mcp add --transport http closedloop-ai https://eu.mcp.closedloop.sh
        ```
      </Tab>

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

        ```json theme={null}
        {
          "mcpServers": {
            "closedloop-ai": {
              "url": "https://mcp.closedloop.sh"
            }
          }
        }
        ```

        For EU workspaces, use `https://eu.mcp.closedloop.sh`.
      </Tab>

      <Tab title="Other Clients">
        Any client supporting MCP HTTP transport with OAuth 2.1:

        | Region | MCP URL                        |
        | ------ | ------------------------------ |
        | US     | `https://mcp.closedloop.sh`    |
        | EU     | `https://eu.mcp.closedloop.sh` |

        Auth is auto-discovered via `/.well-known/oauth-authorization-server`.
      </Tab>
    </Tabs>
  </Step>

  <Step title="Authorize access">
    Your AI tool will show an authorization link. Click it, and your browser opens the ClosedLoop AI sign-in page.

    Log in (or sign up), select your workspace, and click **Connect**.

    <Tip>In Claude Code, type `/mcp` to view connections and trigger authorization.</Tip>
  </Step>

  <Step title="Ask your first question">
    Try one of these:

    * *"What are the top customer pain points?"*
    * *"Show me deal blockers for enterprise customers"*
    * *"How has insight volume changed over the last 3 months?"*

    You should see results from your product intelligence data within seconds.
  </Step>
</Steps>

## Example queries

Once connected, just ask your AI tool naturally:

* *"What are US entertainment customers frustrated about?"*
* *"Which opportunities have the most revenue at risk?"*
* *"What are competitors doing better than us?"*
* *"Build a PRD for calendar management based on customer evidence"*

## What you can do

Once connected, your AI dev agent has access to 12 tools covering:

* **Overview & trends**: aggregate counts, time-series, distribution by category/country/industry
* **Customer intelligence**: search customer accounts, view profiles with deals and revenue context
* **Product intelligence**: hybrid search across all insights with semantic matching
* **Strategic insights**: satisfaction, churn risks, competitor mentions, buying behavior
* **Opportunities**: automatically discovered product problems ranked by business impact with revenue data

<Card title="Full tools reference" icon="wrench" href="/docs/mcp-server/tools">
  See all 12 tools with parameters and return values
</Card>