HyunjunJeon/mcp-for-retriever
If you are the rightful owner of mcp-for-retriever 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.
The Model Context Protocol (MCP) server is a unified platform that integrates multiple retriever services, including web search, vector databases, and relational databases.
Tools
Functions exposed to the LLM to take actions
search_web
Uses Tavily for web search with parameters like query, limit, include_domains, and exclude_domains.
search_vectors
Searches Qdrant vector database with parameters like query, collection, limit, and score_threshold.
search_database
Queries PostgreSQL database with SQL or text, specifying table and limit.
search_all
Performs simultaneous searches across all sources.
health_check
Checks the status of all retrievers.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client