Server profile

MCP Server ChatSum

Query a saved chat database and summarize matching messages through an assistant. ChatSum relies on its companion chatbot to collect messages and connects to Claude Desktop over stdio.

Server facts

MCP Server ChatSum

Project

Author
chatmcp
Website
mcp.so
License
Not specified

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
1,028
Last commit
Data as of

Tags

  • Chat Database
  • Chat Summaries
  • Message Retrieval

Overview

MCP Server ChatSum provides a small assistant-facing interface for querying and summarizing saved chat messages. The README identifies one tool, query_chat_messages, which retrieves messages using supplied parameters and supports summaries based on a query prompt. Its scope is tied to the chat database prepared by the repository's companion chatbot. Before connecting an assistant, users must follow that component's setup instructions and start it so messages are actually saved. The server is therefore a consumer of collected chat history, not a documented replacement for the collection component.

Configuration points the server to its database through CHAT_DB_PATH, either in a root environment file during development or in the MCP client entry. The development workflow uses pnpm to install dependencies and build the project, with a watch command for automatic rebuilds. Claude Desktop configuration launches the built JavaScript entry through a Node executable, and the README gives configuration-file locations for macOS and Windows. Communication uses stdio. A packaged MCP Inspector command is available for debugging the connection through a browser interface. The supplied documentation does not state a license or provide details about query parameters, supported messaging networks, or database retention rules. Those gaps limit how precisely a deployment can be described without consulting material beyond this input.

Install & configure

Requirements

  • Node.js for the documented executable
  • pnpm for dependency installation and builds
  • A chat database populated by the companion chatbot
  • Claude Desktop for the documented integration
Documented launch / install command
path-to/bin/node path-to/mcp-server-chatsum/build/index.js

Replace both example paths with your actual executable and built server location. Set up and run the companion chatbot first, then install dependencies and build with pnpm.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "mcp-server-chatsum": {
      "command": "path-to/bin/node",
      "args": [
        "path-to/mcp-server-chatsum/build/index.js"
      ],
      "env": {
        "CHAT_DB_PATH": "<path to the chat database populated by the companion chatbot>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "mcp-server-chatsum": {
      "command": "path-to/bin/node",
      "args": [
        "path-to/mcp-server-chatsum/build/index.js"
      ],
      "env": {
        "CHAT_DB_PATH": "<path to the chat database populated by the companion chatbot>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "mcp-server-chatsum": {
      "type": "stdio",
      "command": "path-to/bin/node",
      "args": [
        "path-to/mcp-server-chatsum/build/index.js"
      ],
      "env": {
        "CHAT_DB_PATH": "<path to the chat database populated by the companion chatbot>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "mcp-server-chatsum": {
      "command": "path-to/bin/node",
      "args": [
        "path-to/mcp-server-chatsum/build/index.js"
      ],
      "env": {
        "CHAT_DB_PATH": "<path to the chat database populated by the companion chatbot>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "mcp-server-chatsum": {
      "type": "stdio",
      "command": "path-to/bin/node",
      "args": [
        "path-to/mcp-server-chatsum/build/index.js"
      ],
      "env": {
        "CHAT_DB_PATH": "<path to the chat database populated by the companion chatbot>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
query_chat_messagesRetrieve saved messages using supplied parameters and support summaries based on a query prompt.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Summarize messages already collected by the companion chatbot.
  • Query saved chat history using the available retrieval tool.
  • Develop and debug a local Claude Desktop chat-summary integration.

Strengths

  • Provides a focused tool for querying and summarizing saved messages.
  • Documents database-path configuration and Claude Desktop setup.
  • Includes watch-mode builds and an MCP Inspector debugging script.

Limitations

  • Requires separate chatbot setup and message collection first.
  • Query parameter details are not stated in the provided README.
  • License information is not stated in the README.

Frequently asked questions

The README requires setting up and starting the companion chatbot first so that chat messages are saved.

query_chat_messages is the single listed tool, supporting parameterized message queries and prompt-based summaries.

Set CHAT_DB_PATH to the chat database path in the environment or client configuration.

Not stated in the README.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

ghidraMCP

Security & Reverse Engineering

ghidraMCP connects AI assistants to core Ghidra analysis features through a plugin and Python bridge. It supports binary decompilation, renaming methods and data, and browsing methods, classes, imports, and exports.

IDA Pro MCP

Security & Reverse Engineering

IDA Pro MCP connects AI clients to IDA for binary inspection, decompilation, database changes, and optional debugging. Its recommended headless path manages persistent analysis workers and explicit database sessions.

MCP Server for LinkedIn

Communication

Connect an AI assistant to LinkedIn through your own browser session. The server helps you research people and companies, explore jobs, and read conversations from a local installation.

WhatsApp MCP Server

Communication

Connect an assistant to your personal WhatsApp account to search chats, inspect contacts, and send text or media. A Go bridge stores message history locally and serves a Python MCP layer.

Slack MCP Server

Communication

Connect an assistant to Slack channels, threads, DMs, and user information. The server supports filtered history and search, multiple transports, and optional posting or reactions disabled by default.

Telegram MCP

Communication

Telegram MCP connects assistants to Telegram account, chat, message, contact, and media operations through Telethon. It supports multiple accounts and an optional read-only tool surface.