web-search-mcp-server
If you are the rightful owner of web-search-mcp-server 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.
This MCP server provides tools for web search and vector database functionality using LangChain and ChromaDB.
The Web Search MCP Server with ChromaDB Vector Database is designed to facilitate efficient web searches and manage vector databases. It leverages LangChain for web search capabilities and ChromaDB for handling vector embeddings. The server allows users to search documentation for popular libraries, extract content from web pages, and perform semantic similarity searches. It also supports batch operations for efficiency and provides tools to filter documents based on metadata. The server is configured using environment variables and can be run in different transport modes, such as stdio or sse.
Features
- Search documentation for popular libraries (LangChain, LlamaIndex, OpenAI)
- Extract content from web pages
- Store and retrieve documents with vector embeddings
- Perform semantic similarity search
- Batch operations for efficiency
Tools
Web Search
get_docs(query: str, library: str): Search documentation for specified libraries
Vector Database
add_document_to_vectordb(content: str, metadata: Optional[Dict[str, Any]]): Add a single document to ChromaDB
Vector Database
search_vectordb(query: str, top_k: int, filter_criteria: Optional[Dict[str, Any]]): Search the vector database
Vector Database
delete_document_from_vectordb(document_id: str): Delete a document by ID
Vector Database
batch_add_documents_to_vectordb(documents: List[Dict[str, Any]]): Add multiple documents in a batch
