该项目通过MCP协议将本地 LLM（例如 Qwen）连接到计算器或知识库等工具。助手会自动检测并调用这些工具来帮助解答用户疑问。
🔧 通过 MCP 服务器执行工具
🧠 通过 HTTP 或 OpenAI SDK 进行本地 LLM 集成
📚 知识库支持（ data.json ）
⚡ 支持stdio和sse传输
Related MCP server: MCP Server with Local LLM
文件 | 描述 |
| 注册工具并启动 MCP 服务器 |
| 使用 |
| 使用与 OpenAI 兼容的 SDK 实现 LLM + 工具调用逻辑 |
| 使用 stdio 的 MCP 客户端 |
| 使用 SSE 的 MCP 客户端 |
| 问答知识库 |
Python 3.8+
安装依赖项：
pip install -r requirements.txtrequirements.txtaiohttp==3.11.18
nest_asyncio==1.6.0
python-dotenv==1.1.0
openai==1.77.0
mcp==1.6.0python server.py这将启动您的工具服务器，具有add 、 multiply和get_knowledge_base等功能。
python client-http.pypython client-openai.pypython client-stdio.py确保server.py设置：
transport = "sse"然后运行：
python client-sse.pyWhat is 8 times 3?回复：
Eight times three is 24.What are the healthcare benefits available to employees in Singapore?响应将包括来自data.json的相关答案。
data.json[
{
"question": "What is Singapore's public holiday schedule?",
"answer": "Singapore observes several public holidays..."
},
{
"question": "How do I apply for permanent residency in Singapore?",
"answer": "Submit an online application via the ICA website..."
}
]在client-http.py或clientopenai.py中，更新以下内容：
LOCAL_LLM_URL = "..."
TOKEN = "your-api-token"
LOCAL_LLM_MODEL = "your-model"确保您的 LLM 提供与 OpenAI 兼容的 API 端点。
客户端自动处理工具调用和响应。您可以使用Ctrl+C停止服务器或客户端。
MIT 许可证。请参阅LICENSE文件。
This server cannot be deployed
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
LLM Orchestration Agent (Mcp)