Skip to main content
Glama
MCP Test Server

MCP Test Server

by yvanfreitas

MCP Test Server

Este projeto contém dois tipos de servidores:

  1. HTTP Server (server.js) - Um servidor REST API tradicional

  2. MCP Server (mcp-server.js) - Um servidor Model Context Protocol real

⚠️ Diferença Importante

HTTP Server (server.js)

  • ✅ Servidor REST API tradicional

  • ✅ Funciona no navegador (http://localhost:3000)

  • ❌ NÃO compatível com Warp MCP

  • Uso: Testes manuais e desenvolvimento

MCP Server (mcp-server.js)

  • ✅ Servidor MCP real compatível com Warp

  • ✅ Implementa protocolo JSON-RPC via stdio

  • ✅ Expõe ferramentas (tools) para LLMs

  • ❌ Não funciona no navegador

  • Uso: Integração com Warp e outros clientes MCP

Related MCP server: Task Manager MCP Server

Instalação

npm install

Uso

Para HTTP Server (desenvolvimento/testes)

npm start
# Acesse: http://localhost:3000

Para MCP Server (Warp)

npm run mcp

Testando HTTP Server

npm test

Configuração do Warp

O arquivo warp-mcp-config.json está configurado para usar o MCP Server real:

{
  "mcpServers": {
    "mcp-test-server": {
      "command": "node",
      "args": ["mcp-server.js"],
      "working_directory": "C:\\Users\\yvanf\\Documents\\MCP-test"
    }
  }
}

Ferramentas Disponíveis no MCP

  • get_users - Listar usuários

  • get_user - Obter usuário por ID

  • create_user - Criar novo usuário

  • get_tasks - Listar tarefas

  • create_task - Criar nova tarefa

  • search - Buscar usuários e tarefas

License

ISC

Available Tools

8 tools
create_taskC

Create a new task

Inputs: title (required), status, assignedTo.

create_userC

Create a new user

Inputs: name (required), email (required), role.

get_taskC

Get a specific task by ID

Inputs: id (required).

get_tasksB

Get all tasks from the mock database

Inputs: status, assignedTo.

get_userC

Get a specific user by ID

Inputs: id (required).

get_usersC

Get all users from the mock database

Inputs: role.

update_taskC

Update an existing task

Inputs: id (required), title, status, assignedTo.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 8 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose with no ambiguity. The tools are cleanly separated by resource (task vs. user) and action (create, get, update, search), making it easy for an agent to select the correct one. There is no overlap in functionality that would cause confusion.

    Naming Consistency5/5

    The tool names follow a highly consistent verb_noun pattern throughout (e.g., create_task, get_user, update_task). All tools use snake_case and consistent verb choices (create, get, update, search), with no deviations or mixed conventions.

    Tool Count5/5

    With 8 tools, the count is well-scoped and appropriate for the server's purpose of managing tasks and users. Each tool earns its place, covering core operations without being overly sparse or bloated, fitting typical expectations for such a domain.

    Completeness4/5

    The tool set provides strong CRUD coverage for tasks (create, get, update, and implicit delete via absence) and users (create, get), with a search tool for both. A minor gap exists in not having update_user or delete operations explicitly, but agents can work around this with the available tools.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that provides persistent task management capabilities for AI assistants, allowing them to create, update, and track tasks beyond their usual context limitations.
      5
      -
    • A
      license
      A
      quality
      D
      maintenance
      A comprehensive and efficient Model Context Protocol server for task management that works with Claude, Cursor, and other MCP clients, providing powerful search, filtering, and organization capabilities across multiple file formats.
      5
      224 npm
      47
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A remote Model Context Protocol server that enables AI assistants to interact with external services through standardized JSON-RPC, providing tools for basic operations and conversation archiving.
      547 npm
      MIT