MCP Aiven

🚀 Aiven MCP Server

An Model Context Protocol (MCP) server tailored for Aiven.

This service provides access to PostgreSQL, Kafka, ClickHouse, Valkey, and OpenSearch services running on Aiven and across the broader Aiven ecosystem. It also enables integration with more services through native connectors, empowering Large Language Models (LLMs) to build comprehensive stack solutions for all use cases.

✨ Features

Tools

• list_projects

  • Lists all projects in your Aiven account.

• list_services

  • Lists all services within a specific Aiven project.

• get_service_details

  • Retrieves detailed information about a service in a specific Aiven project.

📦 Installation Guide (Claude Desktop)

1. Open the Claude Desktop configuration file located at:

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

2. Add the following content:

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

Update the environment variables:

• Set $REPOSITORY_DIRECTORY to the folder containing the repository.
• Set AIVEN_TOKEN to your Aiven authentication token.

3. Locate the command entry uv and replace it with the absolute path of the uv executable. This ensures that the correct version of uv is used when starting the server. On macOS, you can find this path using which uv.

4. Restart Claude Desktop to apply the changes.

📦 Installation Guide (Cursor)

1. Open Cursor -> Settings -> Cursor Settings.

2. Select "MCP Servers".

3. Add a new server:

   • Name: mcp-aiven
   • Type: command
   • Command: uv --directory $REPOSITORY_DIRECTORY run --with-editable $REPOSITORY_DIRECTORY --python 3.13 mcp-aiven

Here, $REPOSITORY_DIRECTORY is the path to the repository. You may need to add AIVEN_BASE_URL, AIVEN_PROJECT_NAME, and AIVEN_TOKEN as variables.

💻 Usage Examples

Basic Usage

from aiven_mcp import list_projects, list_services, get_service_details

# Example usage
print("Project list:", list_projects())
print("Service list:", list_services(project_name))
print("Service details:", get_service_details(service_id))

🔧 Technical Details

Development

1. Add the following to the .env file in the root repository directory:

AIVEN_BASE_URL=https://api.aiven.io
AIVEN_TOKEN=$AIVEN_TOKEN

2. Install the dependencies:

pip install "git+https://github.com/AivenXYZ/aiven-cli.git@main"

⚠️ Important Note

• Users have full control over the execution and security of MCP.
• AI agent permissions are directly related to API token permissions.
• Exercise extreme caution when providing credentials to AI agents.
• Manage API tokens strictly following the principle of least privilege.