Aiven
Manage Aiven cloud services like Kafka, PostgreSQL, and Redis via its API.
MCP Aiven Docker
A simple Docker container for the MCP Aiven server.
Setup
- Create a
.env
file with your Aiven credentials:
# Aiven API configuration
AIVEN_BASE_URL=https://api.aiven.io
AIVEN_PROJECT_NAME=your-project-name
# Aiven Authentication Token
AIVEN_TOKEN=your-token-here
- Build and run the Docker container:
docker-compose up -d
- Access the server at http://localhost:8000
API Endpoints
GET /
: HTML page showing the server status and environment variablesGET /api/projects
: JSON response with the list of projects
Stopping the Server
docker-compose down
Aiven MCP Server
An MCP server for Aiven.
Features
Tools
-
list_projects
- List all projects on your Aiven account.
-
list_services
- List all services in a specific Aiven project.
-
get_service_details
- Get the detail of your service in a specific Aiven project.
-
get_metadata
- Get the metadata of a specific Aiven service, currently only working for Aiven for PostgreSQL®.
-
run_query
- Run a query against a specific Aiven service, currently only working for Aiven for PostgreSQL®.
Configuration for Claude Desktop
-
Open the Claude Desktop configuration file located at:
- On macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- On Windows:
%APPDATA%/Claude/claude_desktop_config.json
- On macOS:
-
Add the following:
{
"mcpServers": {
"mcp-clickhouse": {
"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_PROJECT_NAME": "$DEFAULT_PROJECT_NAME",
"AIVEN_TOKEN": "$AIVEN_TOKEN"
}
}
}
}
Update the environment variables:
$REPOSITORY_DIRECTORY
to point to the folder cointaining the repositoryAIVEN_PROJECT_NAME
to the default project nameAIVEN_TOKEN
to the Aiven login token.
-
Locate the command entry for
uv
and replace it with the absolute path to theuv
executable. This ensures that the correct version ofuv
is used when starting the server. On a mac, you can find this path usingwhich uv
. -
Restart Claude Desktop to apply the changes.
Configuration for Cursor
-
Navigate to Cursor -> Settings -> Cursor Settings
-
Select "MCP Servers"
-
Add a new server with
- Name:
mcp-aiven
- Type:
command
- Command:
uv --directory $REPOSITORY_DIRECTORY run --with-editable $REPOSITORY_DIRECTORY --python 3.13 mcp-aiven
- Name:
Where $REPOSITORY_DIRECTORY
is the path to the repository. You might need to add the AIVEN_BASE_URL
, AIVEN_PROJECT_NAME
and AIVEN_TOKEN
as variables
Development
- Add the following variables to a
.env
file in the root of the repository.
AIVEN_BASE_URL=https://api.aiven.io
AIVEN_PROJECT_NAME=$DEFAULT_PROJECT_NAME
AIVEN_TOKEN=$AIVEN_TOKEN
-
Run
uv sync
to install the dependencies. To installuv
follow the instructions here. Then dosource .venv/bin/activate
. -
For easy testing, you can run
mcp dev mcp_aiven/mcp_server.py
to start the MCP server.
Environment Variables
The following environment variables are used to configure the ClickHouse connection:
Required Variables
AIVEN_BASE_URL
: The Aiven API urlAIVEN_PROJECT_NAME
: The default project nameAIVEN_TOKEN
: The authentication token =======
mcp-demo
Demo private repo for testing mcp hosting on Aiven.
Related Servers
MCP Bybit API Interface
An interface for interacting with the Bybit cryptocurrency exchange API.
MCP Server for Kubernetes
A server for managing Kubernetes clusters using the Model Context Protocol.
Freshservice
Interact with Freshservice modules for IT service management operations.
MCP Freshbooks Blockchain
Integrates Freshbooks with blockchain technology for immutable financial records.
MCP Payment Server
An MCP server for processing payments using stdio transport, configured via environment variables.
Stripe
Interact with Stripe API
PayPal by CData
A read-only MCP server for querying live PayPal data, powered by the CData JDBC Driver.
Graphlit
Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a searchable Graphlit project.
Kubernetes
Connect to Kubernetes cluster and manage pods, deployments, services.
APISIX-MCP
APISIX Model Context Protocol (MCP) server is used to bridge large language models (LLMs) with the APISIX Admin API, supporting querying and managing all resources in Apache APISIX.