What is Inkeep?
Inkeep is a platform that manages and provides RAG (retrieval‑augmented generation) over your documentation and product content. You need an account to obtain an API key.
MCP Server Python
@MCP-Mirror
Basic information
About MCP Server Python
Mirror of
MCP Server Python config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryMCP Server Python tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is mCP-server-python?
mcp-server-python is an Inkeep‑powered MCP server that lets you query your product documentation and content using a conversational search tool. It is intended for developers who manage documentation in Inkeep and want to surface that content through MCP‑compatible clients such as Claude Desktop.
How to use mCP-server-python?
Clone the repository, create a virtual environment with uv venv, install dependencies with uv pip install -r pyproject.toml, then obtain an API key from the Inkeep Dashboard. Finally, add the server configuration to your MCP client (e.g., claude_desktop_config.json) with the required environment variables (INKEEP_API_BASE_URL, INKEEP_API_KEY, INKEEP_API_MODEL, INKEEP_MCP_TOOL_NAME, INKEEP_MCP_TOOL_DESCRIPTION).
Key features of mCP-server-python
- Connects to Inkeep’s RAG system for documentation retrieval
- Runs locally via the
uvPython project manager - Exposes a single MCP tool (
search-product-content) for conversational queries - Configurable through environment variables for API key, model, and tool name
- Depends on an active Inkeep account and API integration
Use cases of mCP-server-python
- Provide instant answers from your product docs inside an MCP‑compatible assistant
- Enable developers to search documentation without leaving their coding environment
- Embed a RAG‑powered search tool into custom MCP‑enabled applications
Frequently asked questions
How do I get an API key?
Log in to the Inkeep Dashboard, open your project’s **Integrations** tab, create a new API integration, and copy the generated API key.
What are the runtime dependencies?
You need an Inkeep account with a valid API key and the `uv` Python project manager installed on your system.
Where does the data live?
The queried documentation lives in Inkeep’s cloud system; the server itself runs locally and sends requests to the Inkeep API.
How does the server authenticate?
Authentication is done via an API key provided in the `INKEEP_API_KEY` environment variable. The server uses HTTP transport to the Inkeep API.
More Other MCP servers
Health by Dr Brad
Dr Brad StanfieldHealth by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
Senso MCP for Joomla
sensomediaSenso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
16.7K
YOUB
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Awesome Mlops
visengerA curated list of references for MLOps
14.0K
Comments