How do I add a new tool?
Create a new Python file in the `tools/` directory, implement a main function and a tool call function, then provide a `get_tools()` function returning the tool definition using MCP types.
@xiaozhch5
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"chatdata-mcp-server": {
"command": "uv",
"args": [
"pip",
"install",
"-e",
"."
]
}
}
}Tool 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.
ChatData MCP 服务器 is a server application built on the Model Control Protocol (MCP) that provides a rich tool set, prompt system, and resource system to extend the capabilities of large language models. It allows LLMs to interact with external functions, predefined prompts, and accessible data through standard I/O or SSE communication.
Install dependencies with pip install -e . or uv pip install -e ., then run playwright install. Start the server in stdio mode with server, or in SSE mode with server --transport sse --port 8000. Developers can add custom tools, prompts, and resources by following the provided templates in the respective directories.
Create a new Python file in the `tools/` directory, implement a main function and a tool call function, then provide a `get_tools()` function returning the tool definition using MCP types.
Run `server --transport sse --port 8000`. The server will listen for connections via Server-Sent Events on the specified port.
Python 3.12 and Playwright (for web scraping tools) are required. Use `uv venv --python 3.12` to set up the environment and `playwright install` to install browsers.
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
Open-source MCP to use Blender with any LLM
A curated list of references for MLOps

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.
🚀 The fast, Pythonic way to build MCP servers and clients.
Comments