Inkeep MCP Server

What does “Inkeep” MCP Server do?

The Inkeep MCP Server is a specialized Model Context Protocol (MCP) server designed to connect AI assistants with up-to-date product documentation and content managed in Inkeep. It acts as a bridge, allowing development tools and LLM-powered agents to query and retrieve relevant documentation and product knowledge directly from Inkeep’s APIs. This enhances developer workflows by enabling tasks such as searching product documentation, integrating RAG (Retrieval Augmented Generation) capabilities, and surfacing up-to-date content inside AI-driven development environments. By providing a standardized interface, it simplifies integration and empowers developers to build more intelligent and context-aware assistants and tools.

List of Prompts

• No explicit prompt templates were listed in the repository or documentation.

List of Resources

• No explicit resources are described in the repository or documentation.

List of Tools

• search-product-content
  Retrieves product documentation about Inkeep. The query should be framed as a conversational question about Inkeep.

Use Cases of this MCP Server

• Product Documentation Search
  Developers and AI agents can retrieve the latest product documentation for Inkeep, ensuring that users get authoritative and current information in response to product-related queries.

• RAG (Retrieval Augmented Generation) Integration
  Use as a backend for RAG workflows in AI assistants, enabling them to augment responses with relevant documentation snippets provided by Inkeep.

• Inkeep API Integration in Developer Tools
  Integrate Inkeep’s knowledge base directly inside developer IDEs, chatbots, or support systems, reducing context switching and improving productivity.

• Conversational Product Support
  Power chat-based support bots or assistants that answer complex questions with up-to-date documentation from Inkeep’s managed content.

• Automated Onboarding Assistance
  Serve onboarding information to new users or team members, leveraging Inkeep’s documentation as the source of truth.

How to set it up

Windsurf

No Windsurf-specific setup instructions are provided in the repository.

Claude

1. Clone the repository and set up the environment:

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

2. Obtain your API key from the Inkeep Dashboard.
3. Open your claude_desktop_config.json file.
4. Add the following to the mcpServers section:

   {
       "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."
               }
           }
       }
   }
   

5. Save and restart Claude. Verify by running a product content query.

Securing API Keys:
Make sure to store your API key in environment variables as shown in the env block of the configuration above.

Cursor

No Cursor-specific setup instructions are provided in the repository.

Cline

No Cline-specific setup instructions are provided in the repository.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "inkeep-mcp-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “inkeep-mcp-server” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the information available, Inkeep MCP Server provides a focused and useful tool for product documentation search with clear setup steps and secure API key management. However, the lack of explicit prompt templates, resource listings, and advanced features like sampling or roots lowers its completeness for broader MCP use cases.

Our opinion

I would rate this MCP server a 5/10: It provides a clear, well-documented basic tool for integrating Inkeep product documentation with MCP clients, but lacks broader feature coverage and documentation around prompts, resources, and advanced MCP capabilities.

MCP Score