Inkeep Mcp Server

What is Inkeep Mcp Server about?

Inkeep Mcp Server exposes a lightweight Python service that enables clients to query Inkeep's product documentation using retrieval‑augmented generation (RAG). The server translates incoming requests into calls to the Inkeep API and returns relevant search results, making it easy to integrate contextual product knowledge into AI assistants or applications.

How to use Inkeep Mcp Server?

1. Clone the repository and set up a virtual environment with uv.
2. Install dependencies via uv pip install -r pyproject.toml.
3. Obtain an API key from the Inkeep Dashboard (Integrations → Create Integration → API).
4. Configure your MCP client (e.g., Claude Desktop) by adding an entry to claude_desktop_config.json that points to the server directory, specifies the uv command, and provides the required environment variables:
   • INKEEP_API_BASE_URL
   • INKEEP_API_KEY
   • INKEEP_API_MODEL
   • INKEEP_MCP_TOOL_NAME
   • INKEEP_MCP_TOOL_DESCRIPTION
5. Run the server through the configured client; the MCP client will invoke the Python module inkeep_mcp_server to handle requests.

Key features of Inkeep Mcp Server

• RAG integration: Leverages Inkeep's inkeep‑rag model to fetch context‑aware answers.
• Simple Python deployment: Uses uv for environment management and requires only a pyproject.toml.
• Configurable via environment variables: Easy to swap API keys, models, and tool metadata.
• MCP compliance: Works with any MCP‑compatible client such as Claude Desktop.
• Minimal setup: No additional services; runs directly from the repository.

Use cases of Inkeep Mcp Server

• Enrich AI assistants with up‑to‑date product manuals, FAQs, and support articles.
• Provide sales‑oriented bots with instant access to product specifications.
• Add contextual knowledge to internal tooling for customer support agents.
• Power search‑driven features in enterprise applications without building a custom search backend.

FAQ

Q: Do I need an Inkeep account? A: Yes, an active Inkeep account is required to obtain an API key and access the RAG endpoint.

Q: Can I run the server on Windows? A: Absolutely. Install uv, create a virtual environment, and follow the same steps; just use where uv to locate the executable for the configuration.

Q: Which model does the server use? A: By default it uses inkeep‑rag, but you can change INKEEP_API_MODEL to any model supported by the Inkeep API.

Q: How do I change the tool name or description? A: Modify INKEEP_MCP_TOOL_NAME and INKEEP_MCP_TOOL_DESCRIPTION in the environment configuration.

Q: Is there any Docker support? A: The repository does not include a Dockerfile, but you can containerize the Python service using a standard base image and the same environment variables.

mcp-server-python

Inkeep MCP Server powered by your docs and product content.

Dependencies

• An account on Inkeep to manage and provide the RAG
• uv Python project manager

Local Setup

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

Note the full path of the project, referred to as <YOUR_INKEEP_MCP_SERVER_ABSOLUTE_PATH> in a later step.

Get an 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 on Create
7. A generated API key will appear that you can use to authenticate API requests.

We'll refer to this API key as the <YOUR_INKEEP_API_KEY> in later steps.

Add to your MCP client

Follow the steps in this guide to setup Claude Dekstop.

In your claude_desktop_config.json file, add the following entry to mcpServers.

{
    "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."
            }
        },
    }
}

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