https://github.com/qdrant/mcp-for-docs
MCP server for accessing documentation and code snippets of dev tools. Based on `mcp-server-qdrant`
https://github.com/qdrant/mcp-for-docs
Last synced: 7 months ago
JSON representation
MCP server for accessing documentation and code snippets of dev tools. Based on `mcp-server-qdrant`
- Host: GitHub
- URL: https://github.com/qdrant/mcp-for-docs
- Owner: qdrant
- Created: 2025-04-08T22:30:32.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2025-09-18T08:24:22.000Z (8 months ago)
- Last Synced: 2025-09-26T10:49:03.598Z (8 months ago)
- Language: Python
- Size: 313 KB
- Stars: 6
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MCP for Qdrant Documentation
The idea is to create a PoC for curated documentation MCP server based on `mcp-server-qdrant`.
## Motivation
Default `mcp-server-qdrant` is too general and expects you to put data into it.
But one of the main use-cases for MCP is to provide LLMs with latest and most accurate documentation.
This project should serve as an example of how you can build ready-to-use MCP server for a specific package documentation.
This MCP server is read-only, model is only allowed retrieve data about the documentation.
## Setup
This is a Python project using `uv` for package management.
1. Install `uv` if you haven't already:
```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```
2. Create a virtual environment and install dependencies:
```bash
uv venv
source .venv/bin/activate # On Unix/macOS
# or
.venv\Scripts\activate # On Windows
uv pip install -r requirements.txt
```
3. Install the package in development mode:
```bash
uv pip install -e .
```
## Development
- Use `ruff` for linting and formatting
- The project uses `hatchling` as the build backend
### MCP Server Inspector
```bash
uv run mcp dev qdrant_docs_mcp/server.py
```
### Run for serving
```bash
uv run qdrant_docs_mcp/main.py --transport=sse
```
### Importing libraries
To import a single supported library, run
```bash
uv run -m qdrant_docs_mcp.tools.importer --library 'qdrant-client-python'
```
Alternatively, you can import all supported libraries with
```bash
uv run -m qdrant_docs_mcp.tools.importer --library 'all'
```