sqlite-literature-management-fastmcp
A flexible system for managing various types of sources (papers, books, webpages, etc.) and integrating them with knowledge graphs.
claude mcp add --transport stdio zongmin-yu-sqlite-literature-management-fastmcp-mcp-server python -m fastmcp serve source-manager-server.py \ --env SQLITE_DB_PATH="Path to the SQLite database file (e.g., /path/to/sources.db)"
How to use
This MCP server provides a universal literature/source management capability. It lets you create and manage sources such as papers, webpages, books, videos, and blogs, attach multiple identifiers (e.g., arXiv IDs, DOIs, Semantic Scholar IDs, ISBNs, URLs), and maintain structured notes for each source. You can also link sources to knowledge graph entities and define relationships (discusses, introduces, extends, evaluates, applies, critiques) to support richer connections with your memory graph. The server is designed to integrate with the MCP Memory Server for persistent graph storage, enabling you to leverage your existing knowledge graph as you curate and relate sources.
How to install
Prerequisites:
- Python 3.8+ installed on your system
- Access to install Python packages (pip)
- Optional: a running MCP Memory Server for graph persistence
Step-by-step installation:
-
Create and activate a Python virtual environment (recommended): python -m venv venv source venv/bin/activate # on Windows use: venv\Scripts\activate
-
Install the MCP framework (via pip or your preferred package source): pip install fastmcp # or your environment's package source for MCP tooling
-
Prepare a SQLite database path (as required by this server):
- Point SQLITE_DB_PATH to the database file you intend to use
- If the file does not exist, create it and apply the schema from the README's SQL blocks
-
Run the MCP server instance:
Environment variable provides the database path
export SQLITE_DB_PATH=/path/to/sources.db python -m fastmcp serve source-manager-server.py
-
(Optional) If you deploy in production, consider containerizing the service or running behind a process manager and ensure the MCP Memory Server is reachable for graph persistence.
Additional notes
Tips and common considerations:
- Ensure the SQLITE_DB_PATH points to a writable database; initialize the schema as shown in the README if creating a new DB.
- The server supports multiple identifiers per source, so you can enrich entries with arXiv, DOI, URL, and other IDs over time.
- When linking sources to memory graph entities, provide explicit relation types (discusses, introduces, extends, evaluates, applies, critiques) and add contextual notes for clarity.
- If you encounter connectivity issues with the Memory Server, verify network access and credentials (if any) and confirm the memory server is running and reachable from the MCP server.
- Back up the SQLite database regularly, especially before applying schema migrations or bulk updates.
Related MCP Servers
PPTAgent
An Agentic Framework for Reflective PowerPoint Generation
open-ptc-agent
An open source implementation of code execution with MCP (Programatic Tool Calling)
TradingAgents mode
TradingAgents-MCPmode 是一个创新的多智能体交易分析系统,集成了 Model Context Protocol (MCP) 工具,实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作,提供全面的市场分析、投资建议和风险管理。
ultimate_mcp_server
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems
semantic-scholar-fastmcp
A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
mem0
✨ mem0 MCP Server: A memory system using mem0 for AI applications with model context protocl (MCP) integration. Enables long-term memory for AI agents as a drop-in MCP server.