---
title: "MCP server"
canonical_url: "https://docs.getdx.com/mcp/"
md_url: "https://docs.getdx.com/mcp.md"
last_updated: "2026-06-18"
---

# MCP server
The DX MCP (Model Context Protocol) server acts as a bridge between your DX instance data and any MCP-compatible AI client such as Claude, Cursor, and Windsurf. Connecting it lets your agent query your DX dataset, explore your software ecosystem, and act on failing Scorecard checks directly from the client you already use. It's available as a remotely hosted service or as a locally run server.

> **Looking for create/update/delete operations?**
> The MCP server is intentionally **read-only**. For enabling your ai agent with more DX capabilities — including creating scorecards, managing entities, creating studio reports, and more — connect it with the **[DX CLI](https://docs.getdx.com/cli)** instead.

## Remotely hosted server

The remotely hosted MCP server is available at:

```text
https://ai.getdx.com/mcp
```

### Authentication

Authenticate your MCP requests by providing a bearer token in the Authorization HTTP header. This token can be either an [organization token](https://docs.getdx.com/webapi/overview/#authentication) or [personal access token](https://docs.getdx.com/personal-access-tokens/), but must include the `snapshots:read` scope.

### Authorization

MCP tools only have access to those resources covered by the token's scopes. This excludes the `queryData` tool which requires the `datacloud:query` scope for personal access tokens, but is available on all organization tokens.

### Configuration

#### Claude Code

```bash
claude mcp add --transport http dx-mcp https://ai.getdx.com/mcp --header "Authorization: Bearer [TOKEN]"
```

#### Cursor

Add the following to your Cursor MCP configuration:

```json
{
  "mcpServers": {
    "dx-mcp": {
      "url": "https://ai.getdx.com/mcp",
      "headers": {
        "Authorization": "Bearer [TOKEN]"
      }
    }
  }
}
```

## Local deployment

If you prefer to run the MCP server locally instead of using the hosted version, you can follow the instructions on the `dx-mcp-server` [GitHub repository](https://github.com/get-dx/dx-mcp-server).

## Available Tools

### Entities

| Tool               | Description                                                                          |
| ------------------ | ------------------------------------------------------------------------------------ |
| `listEntities`     | List entities from the DX software catalog, with optional search and type filtering. |
| `getEntityDetails` | Get full details for an entity including its metadata, tasks, and scorecard results. |

### Scorecards & Initiatives

| Tool                   | Description                                                                                                       |
| ---------------------- | ----------------------------------------------------------------------------------------------------------------- |
| `listScorecards`       | List all active scorecards.                                                                                       |
| `getScorecardInfo`     | Get details about a specific scorecard, including its levels and checks.                                          |
| `listInitiatives`      | List all initiatives with summary information.                                                                    |
| `getInitiativeDetails` | Get initiative details along with its progress report across entities.                                            |
| `reviewTasks`          | Given an entity and a set of check IDs, produces a structured plan or executes fixes for failing scorecard tasks. |

### Teams

| Tool             | Description                                                            |
| ---------------- | ---------------------------------------------------------------------- |
| `listTeams`      | List all teams in DX.                                                  |
| `getTeamDetails` | Get details for a specific team by ID, reference ID, or member emails. |

### Data

| Tool        | Description                                                                                                                           |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------- |
| `queryData` | Execute a SQL query against the DX Data Cloud PostgreSQL database. Use `information_schema` when table/column structure is uncertain. |

---

## Available Prompts

| Prompt        | Description                                                                                                                     |
| ------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `reviewTasks` | A guided prompt that walks an AI agent through identifying, analyzing, and resolving failing DX scorecard checks for an entity. |
---

## Sitemap

[Overview of all docs pages](/llms.txt)