How do I set up the chat database for ChatSum?
Move to the `chatbot` directory, follow the README there to set up the chat database, then start the chatbot to begin saving your chat messages.

@mcpservers
Basic information
Query and Summarize your chat messages.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
ChatSum is an MCP (Model Context Protocol) server that summarizes your chat messages. It integrates with a chat database and provides a tool to query and summarize past conversations. It is intended for users who want to extract insights or summaries from stored chat logs.
To use ChatSum, you must first set up a chat database by following the instructions in the chatbot directory and start the chatbot to save your chat messages. Then configure the server by setting the CHAT_DB_PATH environment variable to point to the database file. Finally, add the server configuration to Claude Desktop’s claude_desktop_config.json file, specifying the Node.js command and the path to the built server script.
pnpm watch.Move to the `chatbot` directory, follow the README there to set up the chat database, then start the chatbot to begin saving your chat messages.
ChatSum requires Node.js and pnpm. You install dependencies with `pnpm install` and build the server with `pnpm build`.
Your chat messages are stored in a SQLite database file at the path specified by the `CHAT_DB_PATH` environment variable (e.g., `path-to/mcp-server-chatsum/chatbot/data/chat.db`).
ChatSum communicates over standard input/output (stdio), as is typical for MCP servers. Debugging can be done using the MCP Inspector tool.
The README does not mention any authentication or remote access features. The server is configured locally and communicates via stdio.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Agent-native crypto ads: reach real crypto users from $0.05, paid in USDC via x402. No account.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Mandate Law is a law firm for AI products, agents, and the consumer apps they live in, built so coding agents can work with counsel directly. An agent can check whether a request is in scope and get the fixed fee (free a
Comments