Claude MCP Server
@Surfer12
关于 Claude MCP Server
暂无概览
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"claude-mcp-server-two": {
"command": "docker",
"args": [
"exec",
"-it",
"claude-mcp-server",
"/bin/bash"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Claude MCP Server?
Claude MCP Server is an implementation of the Model Context Protocol (MCP) that provides a standardized way to integrate AI tools and models. It supports multiple AI providers (OpenAI, Anthropic, and Google) and offers built-in tools for code analysis, web interaction, and more. It is intended for developers building MCP-compliant applications.
How to use Claude MCP Server?
Clone the repository, create a .env file with API keys for OpenAI, Anthropic, and Google, and set the default provider. Run the Node.js server with npm run dev or npm start, or use Docker for production. The Python server is also available but less maintained. Interact with the server via MCP-compliant clients using JSON-RPC 2.0.
Key features of Claude MCP Server
- MCP-compliance for seamless tool integration with clients.
- Multi-provider support: OpenAI, Anthropic, and Google Gemini.
- Built-in tools for code generation, analysis, web scraping, and more.
- Both Node.js and Python (FastAPI) server implementations.
- Docker support for easy deployment and development.
- Comprehensive testing with Jest and pytest, plus linting and formatting.
Use cases of Claude MCP Server
- Integrating AI-powered code analysis and generation into MCP-compatible workflows.
- Building custom chatbots or assistants that can execute web requests and scrape data.
- Creating a unified backend for AI tools that can switch between different LLM providers.
- Developing and testing MCP-compliant applications in a containerized environment.
FAQ from Claude MCP Server
What AI providers does Claude MCP Server support?
It supports OpenAI, Anthropic (Claude), and Google (Gemini). The default provider is configured via the DEFAULT_AI_PROVIDER environment variable.
What are the runtime requirements?
Node.js for the primary server, Python 3 with FastAPI for the alternative server. API keys for each provider are required.
How do I run the server in production?
Use Docker: build the image with npm run docker:build and run with npm run docker:run. This starts the Node.js server on port 3000 without hot reloading.
Can I add custom tools?
Yes, the framework is extensible. Tools are defined in src/tools/ (JavaScript) and src/core/mcp_tools.py (Python). Refer to howTO.md for details.
What is the license for Claude MCP Server?
The server itself is licensed under the MIT License, as stated in the project's README.
AI 与智能体 分类下的更多 MCP 服务器
Perplexity Ask MCP Server
ppl-aiThe official MCP server implementation for the Perplexity API Platform
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
评论