Aiven Services MCP Server

Overview

The Aiven MCP server enables AI models to interact with Aiven's managed cloud services, including PostgreSQL, Kafka, ClickHouse, Valkey, and OpenSearch. This integration allows AI agents to access and manage your Aiven infrastructure programmatically.

Installation

Prerequisites

• An Aiven account with an authentication token
• Python 3.13 or higher
• The uv package manager

Setup Instructions

1. Clone the repository:

   git clone https://github.com/Aiven-Open/mcp-aiven.git
   cd mcp-aiven
   

2. Install dependencies:

   uv sync
   source .venv/bin/activate
   

Configuration

For Claude Desktop

1. Open the Claude Desktop configuration file:

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

2. Add the Aiven MCP server configuration:

{
  "mcpServers": {
    "mcp-aiven": {
      "command": "uv",
      "args": [
        "--directory",
        "PATH_TO_REPOSITORY_DIRECTORY",
        "run",
        "--with-editable",
        "PATH_TO_REPOSITORY_DIRECTORY",
        "--python",
        "3.13",
        "mcp-aiven"
      ],
      "env": {
        "AIVEN_BASE_URL": "https://api.aiven.io",
        "AIVEN_TOKEN": "YOUR_AIVEN_TOKEN"
      }
    }
  }
}

3. Replace:

   • PATH_TO_REPOSITORY_DIRECTORY with the absolute path to the cloned repository
   • YOUR_AIVEN_TOKEN with your Aiven authentication token
   • Update the path to uv with the absolute path (find it using which uv on macOS/Linux)

4. Restart Claude Desktop to apply the changes.

For Cursor

1. Navigate to Cursor → Settings → Cursor Settings
2. Select "MCP Servers"
3. Add a new server with:
   • Name: mcp-aiven
   • Type: command
   • Command: uv --directory PATH_TO_REPOSITORY_DIRECTORY run --with-editable PATH_TO_REPOSITORY_DIRECTORY --python 3.13 mcp-aiven
4. Add environment variables:
   • AIVEN_BASE_URL: https://api.aiven.io
   • AIVEN_TOKEN: Your Aiven authentication token

Security Considerations

When using this MCP server, keep in mind:

• Self-Managed Responsibility: You are responsible for the operational management, security, and compliance of the MCP server.
• Permission Control: AI agent capabilities are limited by the permissions of the API token used.
• Credential Handling: Exercise caution when providing credentials to AI agents.
• Principle of Least Privilege: Use API tokens with minimal necessary permissions.
• Token Management: Implement secure token storage and regular rotation.

Troubleshooting

If you encounter issues:

1. Verify your Aiven token is valid and has appropriate permissions
2. Check that the paths in your configuration are correct
3. Ensure Python 3.13 and uv are properly installed
4. For development testing, run mcp dev mcp_aiven/mcp_server.py to start the server directly