https://github.com/inkeep/mcp-server-python
Inkeep MCP Server
https://github.com/inkeep/mcp-server-python
Last synced: 8 months ago
JSON representation
Inkeep MCP Server
- Host: GitHub
- URL: https://github.com/inkeep/mcp-server-python
- Owner: inkeep
- License: mit
- Created: 2025-03-13T02:02:51.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-03-13T07:07:09.000Z (8 months ago)
- Last Synced: 2025-03-13T08:20:52.737Z (8 months ago)
- Language: Python
- Size: 31.3 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-mcp-zh - Inkeep
- awesome-mcp-servers - **mcp-server-python** - Inkeep MCP Server (Python-based) `python` `mcp` `server` `http` `git` `pip install git+https://github.com/inkeep/mcp-server-python` (🤖 AI/ML)
- Awesome-MCP-Servers-directory - Inkeep - RAG Search over your content powered by Inkeep (Search)
- Awesome-Official-MCP-Servers - Inkeep - server-python?style=social) | RAG Search over your content powered by [Inkeep](https://inkeep.com) | | (官方 MCP 服务器列表)
- awesome-mcp-servers - Inkeep - Provides a Retrieval Augmented Generation (RAG) server for accessing product documentation via the Model Context Protocol (MCP) (Table of Contents / AI Services)
- awesome-mcp-servers - Inkeep - RAG Search over your content powered by [Inkeep](https://inkeep.com) (Official Servers)
- toolsdk-mcp-registry - ❌ inkeep-rag - based interactions. (python) (Knowledge & Memory / How to Submit)
- metorial-index - Inkeep MCP Server - Integrates documentation with a powerful API for efficient management and access. Facilitates the development of intelligent applications that seamlessly interact with documentation. (Document Processing)
README
# mcp-server-python
Inkeep MCP Server for your docs!
### Dependencies
- An account on [Inkeep](https://inkeep.com)
- [`uv`](https://github.com/astral-sh/uv)
### Setup
```
git clone git@github.com:inkeep/mcp-server-python.git
cd mcp-server-python
uv venv
uv pip install -r pyproject.toml
```
You'll need these environment variables:
```
INKEEP_API_BASE_URL=https://api.inkeep.com/v1
INKEEP_API_KEY=
INKEEP_API_MODEL=inkeep-rag-20250310
```
To get an API key, go to the Inkeep Portal and create an API Integration.
### `claude_desktop_config.json`
```
{
"mcpServers": {
"your-docs-by-inkeep-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-server-python",
"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-20250310"
}
},
}
}
```
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.