This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

Note

: This feature is available in Enterprise and AWS editions only.

Table of contents

• Enable MCP server
• Configure an MCP client

CloudBeaver can run as a Model Context Protocol (MCP) server. This allows external AI clients execute database operations through CloudBeaver.

What is MCP

Model Context Protocol (MCP) is an open standard that enables AI applications to interact with external systems in a consistent way. Through MCP, AI agents can execute database operations and retrieve results through a standardized interface.

For general information about the protocol, see the official documentation.

The MCP server in CloudBeaver exposes a limited set of database tools. It allows the AI agent to:

• inspect database structure - catalogs, schemas, tables
• retrieve table metadata
• execute SQL and receive results

Enable MCP server

To activate the MCP server:

1. Navigate to Settings -> Administration -> Server Configuration

2. Enable the AI Integration and AI MCP Server options

3. Open the context menu for the connection where you want to use MCP and select Edit Connection.

4. Open the AI tab, select the Enable MCP checkbox, and click Save.

   After you click Save, the MCP configuration section appears. It includes:

   • the generated MCP Endpoint for the selected connection
   • ready-to-copy mcp.json examples for supported MCP clients

   Example:

   {
     "mcpServers": {
       "dbeaver": {
         "type": "http",
         "url": "https://server-example.com/api/mcp/projects/General/datasources/postgres-jdbc-19b9378f1f8-60bb24cfcd2979a7",
         "headers": {
           "Authorization": "Bearer ${token}"
         }
       }
     }
   }
   

   Important: The MCP endpoint is connection-specific. Each connection has its own endpoint and must be configured separately in the client.

5. Generate an API access token and replace ${token} with the generated token.

Configure an MCP client

After you enable MCP for a connection, use the generated configuration snippet to register the server in your MCP client.

Client configuration is performed entirely on the client side. Refer to your client’s documentation for instructions on adding an MCP server.

CloudBeaver works with any MCP-compatible client. Configuration snippets are generated automatically for the following clients:

Client	Reference
VS Code	VS Code documentation
Cursor	Cursor documentation
Claude code	Claude code documentation
ZED	ZED documentation

Tip: For other MCP clients, use the generated endpoint URL and adapt the configuration according to the client’s documentation.