Inkeep RAG Server MCP Server

Overview

The Inkeep MCP Server allows AI assistants to search and retrieve information from your product documentation using Inkeep's Retrieval-Augmented Generation (RAG) capabilities. This integration enables AI models to provide more accurate and contextual responses by referencing your specific knowledge base.

Prerequisites

Before setting up the Inkeep MCP Server, you'll need:

1. An account on Inkeep to manage your documentation and provide the RAG functionality
2. The uv Python project manager installed on your system
3. A compatible MCP client (such as Claude Desktop)

Installation

Step 1: Clone and Set Up the Repository

First, clone the repository and set up the Python environment:

git clone https://github.com/inkeep/mcp-server-python.git
cd mcp-server-python
uv venv
uv pip install -r pyproject.toml

Make note of the full absolute path to the project directory, as you'll need it for configuration.

Step 2: Get an Inkeep API Key

1. Log in to the Inkeep Dashboard
2. Navigate to the Projects section and select your project
3. Open the Integrations tab
4. Click Create Integration and choose API from the options
5. Enter a name for your new API integration
6. Click Create
7. Save the generated API key for use in the next step

Step 3: Configure Your MCP Client

Add the Inkeep MCP Server to your MCP client's configuration. For Claude Desktop, edit your claude_desktop_config.json file to include:

{
    "mcpServers": {
        "inkeep-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "YOUR_INKEEP_MCP_SERVER_ABSOLUTE_PATH",
                "run",
                "-m",
                "inkeep_mcp_server"
            ],
            "env": {
                "INKEEP_API_BASE_URL": "https://api.inkeep.com/v1",
                "INKEEP_API_KEY": "YOUR_INKEEP_API_KEY",
                "INKEEP_API_MODEL": "inkeep-rag",
                "INKEEP_MCP_TOOL_NAME": "search-product-content",
                "INKEEP_MCP_TOOL_DESCRIPTION": "Retrieves product documentation about Inkeep. The query should be framed as a conversational question about Inkeep."
            }
        }
    }
}

Replace YOUR_INKEEP_MCP_SERVER_ABSOLUTE_PATH with the full path to the cloned repository and YOUR_INKEEP_API_KEY with the API key you obtained in Step 2.

Note: You may need to use the full path to the uv executable in the command field. You can find this by running which uv on MacOS/Linux or where uv on Windows.

Customization

You can customize the tool's behavior by modifying the environment variables in your configuration:

• INKEEP_MCP_TOOL_NAME: Change this to a name that reflects the content your tool will search
• INKEEP_MCP_TOOL_DESCRIPTION: Update this to describe the specific documentation or content your tool will access

Usage

Once configured, your AI assistant can use the Inkeep MCP Server to search your product documentation. The assistant will automatically use the tool when it needs to answer questions about your product or service.

For example, you can ask questions like:

• "How do I integrate Inkeep with my website?"
• "What features does Inkeep offer?"
• "How does Inkeep's RAG functionality work?"

The AI will use the Inkeep MCP Server to retrieve relevant information from your documentation and provide accurate answers.