mcp-server-chatsum is an MCP server that indexes your chat history and provides tools to query and produce focused summaries on demand. It offers a simple flow: point the server at a local chat database, run the companion chatbot to ingest messages, and then use the MCP tool to retrieve scoped threads and generate concise syntheses. The tool design lets agents filter by participants, time ranges, or keywords before summarizing, which keeps outputs relevant and reduces hallucinated context. Documentation provides a “before you start” checklist to initialize the dataset and highlights the single tool (query_chat_messages) that returns results and summaries. Although releases are minimal, the code and README are sufficient for local setups and experimentation. It’s a practical utility for converting long chat logs into usable, agent-friendly context.
Features
- Query chat logs by participant, time range, and keywords
- On-the-fly summarization of retrieved messages
- Typed MCP tool for predictable inputs and outputs
- Local chat database ingestion with a companion chatbot
- Lightweight setup for personal knowledge consolidation
- Good building block for research, tickets, or daily notes summaries