MCP Server
@JanithSilva
MCP server that provides tools for metadata retrieval from SharePoint and entity retrieval from a Neo4j knowledge graph using semantic similarity search.
Overview
What is MCP Server?
A Python-based server that provides tools for retrieving metadata from SharePoint's 'Documents' library and querying a Neo4j knowledge graph using semantic similarity search. Built on the FastMCP framework, it is intended for applications needing structured document metadata and entity-relationship information.
How to use MCP Server?
Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, and configure environment variables in a .env file (including SharePoint credentials, Neo4j URI, and embedding model settings). Start the server with python mcp_server.py, then invoke the metadata_retrieve or entity_retrieve tools.
Key features of MCP Server
- Retrieves structured metadata from SharePoint Documents library
- Queries Neo4j knowledge graph with semantic similarity search
- Built on FastMCP framework for tool management
- Configurable via environment variables
- Uses semantic embedding for entity retrieval
Use cases of MCP Server
- Automating metadata extraction from SharePoint for document management
- Finding relevant entities and relationships in a knowledge graph via natural language queries
- Integrating document metadata with knowledge graph data for enhanced search
- Enabling AI assistants to access structured information from both sources
FAQ from MCP Server
What systems does MCP Server integrate with?
SharePoint (Documents library) for metadata and Neo4j for knowledge graph entities. It also requires an embedding model API endpoint and key for semantic search.
What are the prerequisites for running MCP Server?
Python 3.x, a running Neo4j database, access credentials for SharePoint, and an embedding model API (e
