convez.ai
MCP ServerIntegração & APIsIntermediário
rakesh-eltropy

MCP REST API e CLI Client

rakesh-eltropy/mcp-client

Interface REST e CLI para orquestração de servidores MCP com LLM

Ver no GitHub
InicialPluginScore · de 0 a 100

Cliente REST API e CLI para interagir com servidores Model Context Protocol (MCP). Integra-se com LangChain para executar prompts de LLM e suporta múltiplos provedores de modelos (OpenAI, Claude, Gemini, Groq, Ollama). Permite que múltiplos servidores MCP colaborem simultaneamente para responder consultas.

Instalação

$npx convez-ai rakesh-eltropy/mcp-client

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
49
Forks
18
Acompanhando
1
Saúde
28%
Último commit
há 1 ano
Versão
—
Issues abertas
1
Contribuidores
1

Casos de uso

  • Integrar múltiplos servidores MCP em uma aplicação LLM
  • Consultar bancos de dados SQLite e APIs externas via LLM
  • Prototipagem rápida de agentes que usam ferramentas MCP
  • Orquestração de buscas (Brave Search) com análise de dados locais

Veredito

Ferramenta prática para abstrair a complexidade de múltiplos servidores MCP atrás de uma API REST simples. Bom para quem quer experimentar MCP com LLMs diversos sem reescrever integrações.

README

A tradução para o português deste README ainda está na fila.

MCP REST API and CLI Client

A simple REST API and CLI client to interact with Model Context Protocol (MCP) servers.

Key Features

1. MCP-Compatible Servers

  • Supports any MCP-compatible servers servers.
  • Pre-configured default servers:
    • SQLite (test.db has been provided with sample products data)
    • Brave Search
  • Additional MCP servers can be added in the mcp-server-config.json file

2. Integrated with LangChain

  • Leverages LangChain to execute LLM prompts.
  • Enables multiple MCP servers to collaborate and respond to a specific query simultaneously.

3. LLM Provider Support

  • Compatible with any LLM provider that supports APIs with function capabilities.
  • Examples:
    • OpenAI
    • Claude
    • Gemini
    • AWS Nova
    • Groq
    • Ollama
    • Essentially all LLM providers are supported as long as they provide a function-based API. Please refer langchain documentation for more details.

Setup

  1. Clone the repository:

    git clone https://github.com/rakesh-eltropy/mcp-client.git
    
  2. Navigate to the Project Directory After cloning the repository, move to the project directory:

    cd mcp-client
    
  3. Set the OPENAI_API_KEY environment variable:

    export OPENAI_API_KEY=your-openai-api-key
    

    You can also set the OPENAI_API_KEY in the mcp-server-config.json file.

    You can also set the provider and model in the mcp-server-config.json file. e.g. provider can be ollama and model can be llama3.2:3b.

4.Set the BRAVE_API_KEY environment variable:

export BRAVE_API_KEY=your-brave-api-key

You can also set the BRAVE_API_KEY in the mcp-server-config.json file. You can get the free BRAVE_API_KEY from Brave Search API.

  1. Running from the CLI:

    uv run cli.py
    

    To explore the available commands, use the help option. You can chat with LLM using chat command. Sample prompts:

      What is the capital city of India?
    
      Search the most expensive product from database and find more details about it from amazon?
    
  2. Running from the REST API:

    uvicorn app:app --reload
    

    You can use the following curl command to chat with llm:

    curl -X POST -H "Content-Type: application/json" -d '{"message": "list all the products from my local database?"}' http://localhost:8000/chat
    

    You can use the following curl command to chat with llm with streaming:

    curl -X POST -H "Content-Type: application/json" -d '{"message": "list all the products from my local database?", "streaming": true}' http://localhost:8000/chat
    

Contributing

Feel free to submit issues and pull requests for improvements or bug fixes.

Ver o original no GitHub

Bom para

Relacionados