Aiven MCP Early availability

Create and manage Aiven services from AI assistants such as Cursor and Claude Code, including PostgreSQL®, Apache Kafka®, plans, metrics, logs, and service configuration. Enable read-only mode in the configuration tabs below to restrict the server to non-destructive operations, or limit tools to specific services to keep the assistant focused.

Prerequisites

• An Aiven account
• An MCP-compatible client, such as Cursor, Claude Code, Claude Desktop, VS Code, or Gemini CLI
• MCP access enabled for your organization by an admin in the Aiven Console under Admin settings > Authentication > Allow MCP connection

Authentication uses OAuth 2.0 with PKCE; your browser opens on first connect so you can sign in and authorize MCP access.

Install the Aiven MCP

Claude Code

1. Open a terminal.

2. Choose your options below, then run the generated command:

   PermissionsRead-only mode (no create, update, or delete)

   Available tools

   AllPostgreSQLKafkaIntegrations

   claude mcp add --transport http aiven https://mcp.aiven.live/mcp?read_only=true

3. To verify the server is registered, in Claude Code run /mcp. The first time you use the server, your browser opens.

4. Sign in to Aiven and select your organization.

For more information, see the Claude Code MCP documentation.

Verify the connection

1. Run /mcp in Claude Code to verify the server is registered.

2. Try a prompt such as:

   List my Aiven projects.

3. If your client prompts you to allow tool execution, approve the request.

Cursor

For one-click installation:

Add to Cursor

To add the server manually:

1. In your project root, create or edit the .cursor/mcp.json file.
2. Choose your options below, then copy the generated configuration into the file:

PermissionsRead-only mode (no create, update, or delete)

Available tools

AllPostgreSQLKafkaIntegrations

{
  "mcpServers": {
    "aiven": {
      "type": "http",
      "url": "https://mcp.aiven.live/mcp?read_only=true"
    }
  }
}

3. Save the file.
4. Restart Cursor.
5. Open Settings > Tools & MCP.
6. Select aiven and click Connect.

For more information, see the Cursor MCP documentation.

Verify the connection

1. Open Cursor Chat with Cmd+L on macOS or Ctrl+L on Windows/Linux.

2. Try a prompt such as:

   List my Aiven projects.

3. If prompted to allow tool execution, click Allow.

4. To confirm the server is registered, go to Settings > Tools & MCP and check that aiven appears with a connected status.

Claude Desktop

1. Open the Claude Desktop configuration file. If it does not exist, create it:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

   • Windows: %APPDATA%\Claude\claude_desktop_config.json

2. Choose your options below, then add the generated configuration to the file:

   PermissionsRead-only mode (no create, update, or delete)

   Available tools

   AllPostgreSQLKafkaIntegrations

   {
     "mcpServers": {
       "aiven": {
         "type": "http",
         "url": "https://mcp.aiven.live/mcp?read_only=true"
       }
     }
   }

3. Save the file and restart Claude Desktop.

For more information, see the Claude Desktop MCP documentation.

Verify the connection

1. Open a new conversation.

2. Verify that the MCP tools icon appears in the input area.

3. Try a prompt such as:

   List my Aiven projects.

4. If prompted to allow tool execution, click Allow.

VS Code

note

Requires VS Code 1.102 or later with the GitHub Copilot extension installed and enabled.

1. Open your workspace in VS Code.

2. In the workspace root, create a .vscode directory.

3. In the .vscode directory, create or edit the mcp.json file.

4. Choose your options below, then add the generated configuration to the file:

   PermissionsRead-only mode (no create, update, or delete)

   Available tools

   AllPostgreSQLKafkaIntegrations

   {
     "servers": {
       "aiven": {
         "type": "http",
         "url": "https://mcp.aiven.live/mcp?read_only=true"
       }
     }
   }

5. Save the file.

6. Reload VS Code.

7. Open the Command Palette and run MCP: List Servers.

8. Confirm that aiven appears in the list.

For more information, see the VS Code MCP documentation.

Verify the connection

1. Open Copilot Chat in VS Code.

2. Open the Command Palette and run MCP: List Servers.

3. Confirm that aiven appears in the list.

4. Try a prompt such as:

   List my Aiven projects.

5. If prompted to allow tool execution, click Allow.

Gemini CLI

1. Create or edit the ~/.gemini/settings.json file.

2. Add the following configuration:

   PermissionsRead-only mode (no create, update, or delete)

   Available tools

   AllPostgreSQLKafkaIntegrations

   {
     "mcpServers": {
       "aiven": {
         "httpUrl": "https://mcp.aiven.live/mcp?read_only=true"
       }
     }
   }

3. Save the file.

4. Run gemini to start the CLI.

5. Run /mcp auth aiven to sign in via your browser.

6. Run /mcp list to confirm the server is connected.

Verify the connection

1. In the Gemini CLI, try a prompt such as:

   List my Aiven projects.

2. If prompted to allow tool execution, approve the request.

Other clients

1. Open your MCP client configuration.

2. Choose your options below, then add the generated configuration to your client:

   PermissionsRead-only mode (no create, update, or delete)

   Available tools

   AllPostgreSQLKafkaIntegrations

   {
     "mcpServers": {
       "aiven": {
         "url": "https://mcp.aiven.live/mcp?read_only=true"
       }
     }
   }

   Most clients use a configuration similar to the above.

3. Save the file and restart your client.

Some clients require a transport type, such as "type": "http". If the configuration fails, see your client documentation.

Verify the connection

1. Open your AI assistant.

2. Try a prompt such as:

   List my Aiven projects.

3. If your client prompts you to allow tool execution, approve the request.

Local installation

Run the server locally using npx instead of the hosted server. Requires an Aiven API token. Set AIVEN_READ_ONLY="true" to enable read-only mode.

Claude Code

1. Open a terminal.

2. Run the following command, replacing your-token-here with your Aiven API token:

   claude mcp add --scope user aiven-mcp -e AIVEN_TOKEN=your-token-here -e AIVEN_READ_ONLY=false -- npx -y mcp-aiven

3. Run /mcp in Claude Code to verify the server is registered.

Cursor

1. In your project root, create or edit the .cursor/mcp.json file.

2. Add the following configuration, replacing your-token-here with your Aiven API token:

   {
     "mcpServers": {
       "aiven-mcp": {
         "command": "npx",
         "args": ["-y", "mcp-aiven"],
         "env": {
           "AIVEN_TOKEN": "your-token-here",
           "AIVEN_READ_ONLY": "false"
         }
       }
     }
   }

3. Save the file and restart Cursor.

Claude Desktop

1. Open the Claude Desktop configuration file.

2. Add the following configuration, replacing your-token-here with your Aiven API token:

   {
     "mcpServers": {
       "aiven-mcp": {
         "command": "npx",
         "args": ["-y", "mcp-aiven"],
         "env": {
           "AIVEN_TOKEN": "your-token-here",
           "AIVEN_READ_ONLY": "false"
         }
       }
     }
   }

3. Save the file and restart Claude Desktop.

VS Code

1. In the .vscode directory, create or edit the mcp.json file.

2. Add the following configuration, replacing your-token-here with your Aiven API token:

   {
     "servers": {
       "aiven-mcp": {
         "command": "npx",
         "args": ["-y", "mcp-aiven"],
         "env": {
           "AIVEN_TOKEN": "your-token-here",
           "AIVEN_READ_ONLY": "false"
         }
       }
     }
   }

3. Save the file and reload VS Code.

Other clients

1. Open your MCP client configuration.

2. Add the following configuration, replacing your-token-here with your Aiven API token:

   {
     "mcpServers": {
       "aiven-mcp": {
         "command": "npx",
         "args": ["-y", "mcp-aiven"],
         "env": {
           "AIVEN_TOKEN": "your-token-here"
         }
       }
     }
   }

3. Save the file and restart your client.

Security and responsibility

important

MCP tools can perform destructive operations on your Aiven services, including creating, modifying, and deleting services, databases, topics, and data.

AI agents run operations from natural language prompts, which can be misinterpreted. Using the Aiven MCP server can result in damage to or loss of data.

Aiven secures the MCP server and data in transit. Your selected AI agent provider determines how the agent uses your data, including whether it uses that data for training. Review the provider's terms before you enable the integration.

Decide whether to enable MCP access in your organization after evaluating the risks.

Under the shared responsibility model, security and compliance for MCP usage are shared between Aiven and your organization. Aiven secures the platform and API. You are responsible for the following:

• Decide whether to enable MCP in your organization and evaluate the associated risks.
• Control access by scoping API tokens to the minimum permissions needed (principle of least privilege) and rotating them regularly.
• Review AI agent actions before they run, especially for write or delete operations on production resources.
• Configure MCP servers securely, including enabling read-only mode to restrict the server to non-destructive operations.