mcp-qdrant-docs
If you are the rightful owner of mcp-qdrant-docs and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A TypeScript-based MCP server that scrapes website content, indexes it into a Qdrant vector database, and provides a tool to answer questions about the indexed content.
The MCP-Qdrant-Docs server is designed to facilitate the extraction and indexing of website content into a Qdrant vector database. It allows users to query the indexed content using natural language questions. The server scrapes specified websites, processes the content into chunks, and embeds these chunks using a sentence transformer model. These embeddings are stored in a Qdrant collection, enabling efficient retrieval of relevant content in response to user queries. The server is particularly useful for creating tools that can answer questions about specific documentation sites, such as React Router or Gradio, by dynamically generating tool names based on the documentation URL.
Features
- Dynamic Tool Generation: Generates tools dynamically based on the documentation URL, allowing users to query specific documentation sites.
- Content Scraping and Indexing: Scrapes website content, processes it into chunks, and indexes it into a Qdrant vector database for efficient retrieval.
- Natural Language Query Support: Supports natural language queries, enabling users to ask questions about the indexed content and receive relevant answers.
- Command-Line Configuration: Offers command-line options for configuring the server, including start URL, collection name, and embedding model.
- Environment Variable Support: Allows configuration through environment variables, providing flexibility in server setup and operation.
