MCP -For-Local
大家好！我是功能丰富的 MCP 服务，旨在打破设备与服务的隔阂，为用户带来便捷体验。 天气工具和气象平台联动，快速为用户推送全球实时天气，助力大家规划出行。控制浏览器工具模拟人工操作，自动搜索、浏览网页，大幅节省时间。摄像头工具调用本地摄像头拍照、录像，实现人脸识别，保障家庭安防。 为实现工具协同，我搭建了稳定框架，开发者可以基于现有服务进行拓展
claude mcp add --transport stdio dreamboat-rachel-mcp-server-for-local uv run client/mcp_client.py proxy/proxy_server.py \ --env MODEL="Model name (default: qwen-max)" \ --env BASE_URL="Base URL for the ComfyUI server" \ --env LOG_LEVEL="Logging level (DEBUG, INFO, WARNING, ERROR)" \ --env CHROME_PATH="Chrome browser executable path" \ --env CONFIG_FILE="Path to server configuration file" \ --env SERVERS_DIR="Directory containing server scripts" \ --env GAODE_API_KEY="Gaode (Amap) API key for weather queries" \ --env CHROMEDRIVER_PATH="ChromeDriver executable path" \ --env DASHSCOPE_API_KEY="DashScope API key"
How to use
This MCP server provides a local proxy and client setup with multiple AI tool calls integrated via MCP. It exposes capabilities such as real-time weather lookups, Google-style search, camera control for taking photos, image generation through ComfyUI, and an intelligent dialogue system built on DashScope. To use it, run the client and proxy pair provided in the repository to start the local MCP environment, then interact with the client to issue commands like asking about the weather in a city, performing a web search, capturing an image, generating artwork, or engaging in a multi-turn chat session. The system supports extending functionality by adding new tools under the tools directory and registering them in the configuration.
How to install
Prerequisites:
- Python 3.8+
- Git
- Optional: Chrome and ChromeDriver for web-related tooling
Installation steps:
- Clone the repository and navigate to the project:
git clone https://github.com/yourusername/mcp-server-for-local.git
cd mcp-server-for-local
- Create and activate a Python virtual environment:
# Windows
python -m venv .venv
.venv\Scripts\activate
# Linux
python3 -m venv .venv
source .venv/bin/activate
- Install dependencies using uv (as recommended by the project):
uv pip install -r requirements.txt
# If network issues occur, use a mirror:
uv pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
- Copy and configure environment variables:
cp .env.example .env
Edit the .env file to include required keys such as DASHSCOPE_API_KEY and GAODE_API_KEY, along with model and paths for Chrome/ChromeDriver if needed. 5) Run the server and client as described in the usage section.
Additional notes
Tips and common issues:
- Ensure your environment variables are correctly set in the .env file or via the provided env block in mcp_config.
- If dependency installation fails due to network issues, use a domestic PyPI mirror and clear uv cache if needed.
- For Chrome-related tooling, ensure Chrome and ChromeDriver versions are compatible and that CHROME_PATH and CHROMEDRIVER_PATH point to valid executables.
- If you modify or extend tools under src/mcp/tools, remember to register new tools in the configuration and provide tests.
- The logging level can be adjusted with LOG_LEVEL to help with debugging during development or production runs.
Related MCP Servers
mcp-vegalite
MCP server from isaacwasserman/mcp-vegalite-server
github-chat
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
pagerduty
PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.
futu-stock
mcp server for futuniuniu stock
mcp -boilerplate
Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP
