Mcp Server Chatsum

What is Mcp Server Chatsum about?

Mcp Server Chatsum provides a tool to query stored chat messages and generate summaries based on custom prompts. It works with a local SQLite chat database created by the companion chatbot project.

How to use Mcp Server Chatsum?

1. Configure the environment variable CHAT_DB_PATH to point to your chat.db file.
2. Install dependencies with pnpm install and build the server (pnpm build).
3. Run the server via the MCP configuration (e.g., using Claude Desktop) or the provided npx command.
4. Invoke the query_chat_messages tool with desired query parameters and a summarization prompt.

Key features of Mcp Server Chatsum

• Query Chat Messages: Retrieve messages using filters like time range, participants, or keywords.
• Summarization: Apply a custom prompt to produce concise summaries of the queried conversation.
• Easy Integration: Communicates over stdio, compatible with any MCP‑enabled client.
• Development Friendly: Supports auto‑rebuild mode (pnpm watch) and debugging via MCP Inspector.

Use cases of Mcp Server Chatsum

• Generate meeting minutes from daily chat logs.
• Create concise reports for customer support conversations.
• Summarize knowledge base discussions for quick review.
• Feed summarized chat content into downstream AI agents.

FAQ from the Mcp Server Chatsum

• Do I need a specific database format? Yes, the server expects a SQLite database generated by the chatbot project.
• Can I customize the summarization prompt? Absolutely, the query_chat_messages tool accepts any prompt you provide.
• Is there a way to debug issues? Use the built‑in MCP Inspector (pnpm inspector) for interactive debugging.
• What platforms are supported? Any platform that can run Node.js; configuration examples are provided for macOS and Windows.

mcp-server-chatsum

This MCP Server is used to summarize your chat messages.

中文说明

Before you start

move to chatbot directory, follow the README to setup the chat database.

start chatbot to save your chat messages.

Features

Resources

Tools

• query_chat_messages - Query chat messages
  • Query chat messages with given parameters
  • Summarize chat messages based on the query prompt

Prompts

Development

1. Set up environment variables:

create .env file in the root directory, and set your chat database path.

CHAT_DB_PATH=path-to/chatbot/data/chat.db

2. Install dependencies:

pnpm install

Build the server:

pnpm build

For development with auto-rebuild:

pnpm watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server-chatsum": {
      "command": "path-to/bin/node",
      "args": ["path-to/mcp-server-chatsum/build/index.js"],
      "env": {
        "CHAT_DB_PATH": "path-to/mcp-server-chatsum/chatbot/data/chat.db"
      }
    }
  }
}

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

pnpm inspector

The Inspector will provide a URL to access debugging tools in your browser.

Community

• MCP Server Telegram
• MCP Server Discord

About the author

• idoubi