What is Inkeep?

Inkeep is a Retrieval-Augmented Generation (RAG) search engine that allows users to search over their content. It provides an MCP (Model Context Protocol) server powered by user documents and product content. This makes it easy to integrate with other tools using the MCP standard.

How to use Inkeep MCP Server?

1. Local Setup
   • Clone the repository and set up a Python virtual environment
   • Install dependencies using uv
2. Get an Inkeep API key
   • Create a project in the Inkeep Dashboard
   • Set up an API integration to obtain an API key
3. Configure MCP client
   • Add Inkeep MCP server configuration to your Claude Desktop or other MCP-compatible client
   • Set the required environment variables including the API key and endpoint

Key features of Inkeep MCP Server

• RAG-based search over your content
• Integration with the Model Context Protocol standard
• Easy setup and configuration
• Customizable tool name and description for API endpoints

Use cases of Inkeep MCP Server

1. Searching your product documentation content
2. Integrating knowledge bases with AI chat systems
3. Retrieving specific information from corporate or personal documents
4. Enabling contextual searches within applications that use the MCP standard

FAQ about Inkeep MCP Server

• What dependencies are required?

  An Inkeep account and uv Python project manager

• How do I authenticate API requests?

  Use the API key generated in the Inkeep Dashboard integration setup

• Can I customize tool descriptions?

  Yes, you can customize the tool name and description in the configuration

• Where is the official documentation?

  The complete setup guide is available on Model Context Protocol documentation

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 in a later step. ## Get an API key 1. Log in to the [Inkeep Dashboard](https://portal.inkeep.com) 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 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. json claude_desktop_config.json { "mcpServers": { "inkeep-mcp-server": { "command": "uv", "args": [ "--directory", "", "run", "-m", "inkeep_mcp_server" ], "env": { "INKEEP_API_BASE_URL": "https://api.inkeep.com/v1", "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.