Skip to main content
The Aiven Model Context Protocol (MCP) server enables AI-powered tools to access Aiven documentation directly. Connect your favorite AI coding assistant to get contextual help about Aiven services, APIs, and best practices while you work.

​
What is MCP?

The Model Context Protocol is an open standard that allows AI applications to securely access external data sources and tools. The Aiven MCP server provides:
  • Real-time documentation access: Query the latest Aiven documentation
  • Contextual answers: Get relevant answers about Aiven services
  • Code examples: Access integration examples and code snippets
  • Best practices: Learn recommended patterns and configurations

​
Supported clients

The Aiven MCP server works with these AI tools:

Cursor

AI-powered code editor

Claude Code

Command-line AI assistant

Claude Desktop

Desktop AI application

VS Code

With GitHub Copilot

ChatGPT

Web-based AI chat

Other clients

Any MCP-compatible client

​
Server URL

Use this URL when configuring your MCP client: 
https://aiven-docs.mcp.kapa.ai

​
Prerequisites

  • An MCP-compatible client (see supported clients above)
  • A Google account for authentication (required by some clients)

​
Setup guides

​
Cursor

Configure Cursor to access Aiven documentation:
1

Create MCP configuration

In your project root, create or edit .cursor/mcp.json:
.cursor/mcp.json
{
  "mcpServers": {
    "aiven": {
      "type": "http",
      "url": "https://aiven-docs.mcp.kapa.ai"
    }
  }
}
2

Restart Cursor

Close and reopen Cursor for the configuration to take effect
3

Connect to the server

  1. Open Settings > Tools & MCP
  2. Find aiven in the list
  3. Click Connect
  4. Sign in with your Google account when prompted
4

Verify connection

Ask the Cursor AI: “How do I create a Kafka topic in Aiven?”If the response references Aiven documentation, you’re connected!
Learn more about Cursor MCP

​
Claude Code

Add Aiven documentation to Claude’s command-line interface:
1

Install the server

Run this command in your terminal:
claude mcp add --transport http aiven-docs https://aiven-docs.mcp.kapa.ai
2

Authenticate

Sign in with your Google account when prompted
3

Verify installation

claude mcp
You should see aiven-docs in the list of registered servers
4

Test it out

Ask Claude: “Explain how to use the Aiven CLI to create a PostgreSQL service”
Learn more about Claude Code MCP

​
Claude Desktop

Connect Aiven documentation to Claude Desktop app:
1

Locate configuration file

Open the Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
Create the file if it doesn’t exist:
mkdir -p ~/Library/Application\ Support/Claude
touch ~/Library/Application\ Support/Claude/claude_desktop_config.json
2

Add configuration

Edit the file and add:
claude_desktop_config.json
{
  "mcpServers": {
    "aiven": {
      "type": "http",
      "url": "https://aiven-docs.mcp.kapa.ai"
    }
  }
}
3

Restart Claude Desktop

Quit and reopen the Claude Desktop application
4

Authenticate

Sign in with your Google account when prompted
5

Test the connection

Ask: “How do I configure VPC peering for Aiven services?”
Learn more about Claude Desktop MCP

​
VS Code

Use Aiven documentation with GitHub Copilot in Visual Studio Code:
Requires Visual Studio Code 1.102 or later with GitHub Copilot extension installed.
1

Create MCP configuration

In your workspace root, create .vscode/mcp.json:
.vscode/mcp.json
{
  "servers": {
    "aiven": {
      "type": "http",
      "url": "https://aiven-docs.mcp.kapa.ai"
    }
  }
}
2

Reload VS Code

Reload the window: Ctrl+Shift+P (or Cmd+Shift+P on macOS) → Developer: Reload Window
3

Verify server

Open Command Palette and run MCP: List ServersConfirm aiven appears in the list
4

Authenticate

Sign in with your Google account when prompted
5

Use with Copilot

In Copilot Chat, ask: “Show me how to create an Aiven for PostgreSQL service using Terraform”
Learn more about VS Code MCP

​
ChatGPT (Web)

Add Aiven documentation access to ChatGPT:
ChatGPT UI may change. Refer to OpenAI’s documentation if steps don’t match.
1

Enable developer mode

  1. Open ChatGPT
  2. Click Settings
  3. Go to Apps → Advanced settings
  4. Enable Developer mode
2

Create MCP app

  1. Go to Apps → Create app
  2. Enter details:
    • Name: Aiven
    • Description: Aiven documentation MCP server
    • MCP Server URL: https://aiven-docs.mcp.kapa.ai
  3. Click Create
3

Authenticate

Sign in with your Google account when prompted
4

Verify setup

Check that Aiven appears under Settings → Apps
5

Start using

In a new chat, ask: “How do I set up Apache Kafka ACLs on Aiven?”
Learn more about OpenAI Developer Mode

​
Other clients

For other MCP-compatible clients:
1

Find configuration location

Check your client’s documentation for MCP server configuration
2

Add server configuration

Most clients accept a configuration similar to:
{
  "mcpServers": {
    "aiven": {
      "url": "https://aiven-docs.mcp.kapa.ai"
    }
  }
}
Some clients require specifying the transport type:
{
  "mcpServers": {
    "aiven": {
      "type": "http",
      "url": "https://aiven-docs.mcp.kapa.ai"
    }
  }
}
3

Restart your client

Restart the application for changes to take effect
4

Authenticate

Sign in with your Google account if prompted

​
Using the MCP server

Once connected, you can ask your AI assistant questions about Aiven:

​
Example questions

How do I create my first Aiven for PostgreSQL service?
What are the steps to set up a Kafka cluster on Aiven?
How do I connect to an Aiven service from my application?

​
Example conversation

You: How do I create an Apache Kafka topic using the Aiven CLI? AI: Based on the Aiven documentation, you can create a Kafka topic using the avn CLI: 
avn service topic-create my-kafka \
  my-topic \
  --partitions 3 \
  --replication 2 \
  --retention 72h
This creates a topic named my-topic on the service my-kafka with:
  • 3 partitions
  • Replication factor of 2
  • 72-hour retention period
You can list all topics with: 
avn service topic-list my-kafka
For more details, see the Aiven CLI documentation.

​
Enabling tool execution

Some clients require permission to execute MCP tools:
  1. When prompted “Allow tool execution?”, click Allow
  2. This grants the AI permission to query Aiven documentation
  3. You’ll only need to approve once per session

​
Troubleshooting

Solutions:
  • Verify the configuration file path is correct
  • Check JSON syntax (use a JSON validator)
  • Ensure the file is saved
  • Restart your client application
  • Check client logs for errors
Solutions:
  • Ensure you’re using a Google account
  • Check your internet connection
  • Try clearing browser/client cache
  • Use an incognito/private window
  • Check if corporate firewall blocks authentication
Solutions:
  • Explicitly mention Aiven in your questions
  • Try: “According to Aiven documentation, how do I…”
  • Verify the server is connected (check client settings)
  • Enable tool execution when prompted
  • Check if the client shows MCP server status
The MCP server uses the latest published Aiven documentation. If information seems outdated:
  • Verify you’re asking about current features
  • Check the Aiven Documentation directly
  • Report issues to Aiven support

​
Privacy and security

How your data is handled:
  • Questions are sent to the MCP server for documentation lookup
  • No code or proprietary data is required
  • Authentication uses Google OAuth (handled by Google)
  • The server retrieves public Aiven documentation only
  • No conversation history is stored permanently
See Aiven’s privacy policy and Kapa’s privacy policy for details.

​
MCP server provider

The Aiven MCP server is hosted by Kapa.ai, a platform for AI-powered documentation access. Kapa provides:
  • Reliable hosting: High-availability MCP server infrastructure
  • Real-time sync: Automatic updates from Aiven documentation
  • Security: OAuth authentication and encrypted communication
  • Performance: Fast response times for documentation queries
Learn more about Kapa’s MCP integration.

​
Limitations

Current limitations:
  • Only accesses public Aiven documentation
  • Cannot access your specific Aiven account or services
  • No real-time service status information
  • Cannot execute commands or make changes
  • Requires internet connection
  • Google account required for authentication
For account-specific help, use the Aiven Console or contact Aiven Support.

Build docs developers (and LLMs) love

Get started for freeTalk to us