ChatSum
Query and summarize your chat messages with AI prompts.
What is ChatSum?
ChatSum is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to query and summarize your chat messages with ai prompts.
Query and summarize your chat messages with AI prompts.
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Query and summarize your chat messages with AI prompts.
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx chatsumConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ChatSum
mcp-server-chatsum is a TypeScript MCP server that connects your AI assistant to a local SQLite chat database, exposing a query_chat_messages tool that retrieves and summarizes conversation history on demand. It is designed to work alongside a companion chatbot application that populates the SQLite database, giving AI models a structured way to search past conversations, extract recurring topics, and summarize long chat threads without manually exporting logs. Developers and power users run it to bring months of chat history into their AI workflows for analysis, recall, and synthesis.
Prerequisites
- Node.js 18 or later and pnpm
- A running chatbot application that writes messages to a SQLite database (chat.db)
- The path to the chat.db file on your filesystem
- An MCP client such as Claude Desktop
Set up the companion chatbot application
mcp-server-chatsum reads from a SQLite database populated by a separate chatbot app. Clone or install that chatbot first and follow its README so that chat.db is created and contains messages.
Clone and build the MCP server
Clone the mcp-server-chatsum repository, install dependencies with pnpm, and build the TypeScript source.
git clone https://github.com/chatmcp/mcp-server-chatsum.git
cd mcp-server-chatsum
pnpm install
pnpm buildLocate your chat database path
Find the absolute path to the chat.db file created by your chatbot application. You will pass this path as the CHAT_DB_PATH environment variable to the MCP server.
# Example paths
# macOS: /Users/yourname/chatbot/data/chat.db
# Linux: /home/yourname/chatbot/data/chat.db
# Windows: C:\Users\yourname\chatbot\data\chat.dbConfigure your MCP client
Add mcp-server-chatsum to your MCP client configuration, providing the absolute path to the built index.js and setting CHAT_DB_PATH to your chat database location.
{
"mcpServers": {
"chatsum": {
"command": "node",
"args": ["/absolute/path/to/mcp-server-chatsum/dist/index.js"],
"env": {
"CHAT_DB_PATH": "/absolute/path/to/chatbot/data/chat.db"
}
}
}
}Restart your MCP client and verify
Restart Claude Desktop or your MCP client. Ask it to summarize recent chats to confirm the server is connected and reading from the database.
ChatSum Examples
Client configuration
Claude Desktop configuration for mcp-server-chatsum with the database path set.
{
"mcpServers": {
"chatsum": {
"command": "node",
"args": ["/home/user/mcp-server-chatsum/dist/index.js"],
"env": {
"CHAT_DB_PATH": "/home/user/chatbot/data/chat.db"
}
}
}
}Prompts to try
Example prompts once the server is connected to your chat database.
- "Summarize the conversations I had this week and highlight the main topics."
- "Find all messages where we discussed project deadlines and list the key dates mentioned."
- "What questions did I ask most frequently in the past month?"
- "Summarize the last 50 messages in my chat history."
- "Were there any action items mentioned in my chats from last Monday?"Troubleshooting ChatSum
Server errors with 'database not found' or 'SQLITE_CANTOPEN'
The CHAT_DB_PATH environment variable must point to the exact absolute path of the chat.db file. Verify the file exists at that path and that the process has read permission. On Windows, use forward slashes or escaped backslashes.
query_chat_messages returns no results
Confirm the companion chatbot application is running and has written messages to the database. Open chat.db with a SQLite browser (e.g., DB Browser for SQLite) to verify rows exist in the messages table.
Build fails with pnpm errors
Ensure pnpm is installed (npm install -g pnpm) and that Node.js 18+ is active. Delete node_modules and run pnpm install again if you encounter dependency resolution errors.
Frequently Asked Questions about ChatSum
What is ChatSum?
ChatSum is a Model Context Protocol (MCP) server that query and summarize your chat messages with ai prompts. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ChatSum?
Follow the installation instructions on the ChatSum GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ChatSum?
ChatSum works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ChatSum free to use?
Yes, ChatSum is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
ChatSum Alternatives — Similar Communication Servers
Looking for alternatives to ChatSum? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ChatSum in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ChatSum?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.