chatdata-mcp-server

# ChatData MCP Server The ChatData MCP Server is a service application based on the Model Control Protocol (MCP), providing a rich toolkit and prompt system to enhance the capabilities of large language models. ## Project Overview This project offers a flexible server framework that allows interaction with large language models via the MCP protocol. The server can: - Execute various tool functions to extend the model's capabilities - Provide preset prompt templates to simplify common tasks - Support communication via standard input/output or SSE - Automatically discover and register newly added tools and prompts ## Core Components ### Tool System (`tools/`) The tools module provides various functional extensions that enable the language model to perform specific tasks: - **Network Tools**: - `web_scraper.py` - Web content scraping tool - `ip_info.py` - IP address information query tool - `http_client.py` - HTTP request client - `fetch.py` - Simple web fetching tool - `browser_use.py` - Network information retrieval based on browser_use - **Data Processing Tools**: - `data_converter.py` - Data format conversion tool (JSON/YAML/XML) - `text_summary.py` - Text summarization tool - `calculator.py` - Advanced mathematical calculation tool - **Development Utility Tools**: - `code_formatter.py` - Code formatting tool - `postgres.py` - PostgreSQL database query tool - **Multimedia Tools**: - `image_gen.py` - Image generation tool - **Other Utility Tools**: - `translator.py` - Text translation tool - `weather.py` - Weather query tool - `echo.py` - Simple echo tool ### Prompt System (`prompts/`) The prompts module provides various preset prompt templates for quickly generating high-quality responses: - `simple.py` - Basic prompt template - `content_generator.py` - Content generation prompt - `code_review.py` - Code review prompt - `utils.py` - Prompt utility functions ### Server Component (`server/`) The server module handles client requests and responses, supporting multiple communication methods: - Standard input/output (stdio) mode - Server-Sent Events (SSE) mode ## Installation and Usage ``` uv venv --python 3.12 ``` ### Install Dependencies ```bash pip install -e . ``` Or use `uv`: ```bash uv pip install -e . ``` Install playwright ```bash playwright install ``` ### Start the Server #### stdio Mode (Default) ```bash server ``` #### SSE Mode ```bash server --transport sse --port 8000 ``` ## Development Guide ### Adding New Tools 1. Create a new Python file in the `tools/` directory 2. Implement a main function and a tool invocation function 3. Provide a `get_tools()` function to return tool definitions Example: ```python import mcp.types as types async def my_function(param1, param2): # Implement functionality return [types.TextContent(type="text", text="Result")] async def my_tool(name: str, arguments: dict): if name != "my_tool": raise ValueError(f"Unknown tool: {name}") # Extract parameters param1 = arguments.get("param1") param2 = arguments.get("param2") return await my_function(param1, param2) def get_tools(): return [ types.Tool( name="my_tool", description="Tool description", inputSchema={ "type": "object", "required": ["param1"], "properties": { "param1": { "type": "string", "description": "Parameter 1 description", }, "param2": { "type": "string", "description": "Parameter 2 description", } }, }, ) ] ``` ### Adding New Prompts 1. Create a new Python file in the `prompts/` directory 2. Implement a prompt generation function 3. Provide a `get_prompts()` function to return prompt definitions Example: ```python import mcp.types as types from .utils import create_messages def my_prompt(context=None, topic=None): messages = create_messages(context, topic) return types.GetPromptResult( messages=messages, description="Prompt description" ) def get_prompts(): return [ types.Prompt( name="my_prompt", description="Prompt description", func=my_prompt, args={ "context": { "type": "string", "description": "Context information" }, "topic": { "type": "string", "description": "Topic" } } ) ] ``` ## License MIT