# CData Connect AI MCP server

> Query enterprise data sources from your AI assistant through CData's cloud-hosted Connect AI service.

- Listing: https://mcp.tc/i/cdata-connect-ai
- Connect: use the server's own URL `https://mcp.cloud.cdata.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Databases & Backend](https://mcp.tc/c/databases)
- Vendor: CData
- Homepage: <https://www.cdata.com/ai/>
- Docs: <https://cloud.cdata.com/docs/MCP.html>

## About

CData Connect AI is a cloud-hosted MCP server that gives an AI assistant access to the enterprise data sources configured in a CData Connect AI account. CData describes support for more than 300 sources, so databases, SaaS apps and other systems can be queried through one endpoint.

It runs as a hosted streamable HTTP endpoint at mcp.cloud.cdata.com. Users sign in with OAuth (openid, profile and email scopes) and need a CData Connect AI account with data sources already set up. Nothing is installed locally. The tool list is not published without signing in.

## What it can do

- Access enterprise data sources configured in CData Connect AI
- Query connected data in natural language from an AI assistant
- Sign in with OAuth so access follows your CData account

## Example prompts

- "List the data sources available in my CData Connect AI account"
- "Show the 20 most recent orders from my connected sales database"
- "Which tables are available in my Salesforce connection?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http cdata-connect-ai https://mcp.cloud.cdata.com/mcp
```

2. Start Claude Code, type `/mcp`, pick **cdata-connect-ai** and choose **Authenticate**. A browser window opens for the CData sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

2. Name it **CData Connect AI** and paste this URL:

```url
https://mcp.cloud.cdata.com/mcp
```

3. Click **Add**, then **Connect**, and sign in when CData asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=CData%20Connect%20AI&connectorUrl=https%3A%2F%2Fmcp.cloud.cdata.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://mcp.cloud.cdata.com/mcp` and click **Add**.

3. Click **Connect** and sign in when CData asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://mcp.cloud.cdata.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to CData to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=cdata-connect-ai&config=eyJ1cmwiOiJodHRwczovL21jcC5jbG91ZC5jZGF0YS5jb20vbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "cdata-connect-ai": {
      "url": "https://mcp.cloud.cdata.com/mcp"
    }
  }
}
```

Cursor shows **Needs login** next to the server. Click it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=cdata-connect-ai&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.cloud.cdata.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"cdata-connect-ai","type":"http","url":"https://mcp.cloud.cdata.com/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "cdata-connect-ai": {
      "type": "http",
      "url": "https://mcp.cloud.cdata.com/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "cdata-connect-ai": {
      "serverUrl": "https://mcp.cloud.cdata.com/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add cdata-connect-ai --url https://mcp.cloud.cdata.com/mcp
codex mcp login cdata-connect-ai
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.cdata-connect-ai]
url = "https://mcp.cloud.cdata.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http cdata-connect-ai https://mcp.cloud.cdata.com/mcp
```

Then, inside Gemini CLI, run `/mcp auth cdata-connect-ai` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "cdata-connect-ai": {
      "type": "http",
      "url": "https://mcp.cloud.cdata.com/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.cloud.cdata.com/mcp`.

## Details

- Server version: 1.0.0
- Last checked: 2026-10-03 (reachable, asks for credentials)
- Listed: 2026-10-03
- Updated: 2026-10-03

---
Source: https://mcp.tc/i/cdata-connect-ai (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report