rdwj/mcp-test-mcp

mcp-test-mcp

An MCP server that helps AI assistants test other MCP servers. It provides tools to connect to target MCP servers, discover their capabilities, execute tools, read resources, and test prompts—all through proper MCP protocol communication.

Features

• Connection Management: Connect to any MCP server (STDIO or HTTP transport), auto-detect protocols, track connection state
• Tool Testing: List all tools with complete input schemas, call tools with arbitrary arguments, get detailed execution results
• Resource Testing: List all resources with metadata, read text and binary content
• Prompt Testing: List all prompts with argument schemas, get rendered prompts with custom arguments
• LLM Integration: Execute prompts end-to-end with actual LLM inference, supports template variables and JSON extraction

Installation

Prerequisites: Node.js 16+ and Python 3.11+

Choose your AI coding tool:

{
  "mcpServers": {
    "mcp-test-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-test-mcp"]
    }
  }
}

claude mcp add mcp-test-mcp -- npx -y mcp-test-mcp

{
  "mcpServers": {
    "mcp-test-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-test-mcp"]
    }
  }
}

{
  "mcpServers": {
    "mcp-test-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-test-mcp"]
    }
  }
}

{
  "servers": {
    "mcpTestMcp": {
      "command": "npx",
      "args": ["-y", "mcp-test-mcp"]
    }
  }
}

codex mcp add mcp-test-mcp -- npx -y mcp-test-mcp

[mcp_servers.mcp-test-mcp]
command = "npx"
args = ["-y", "mcp-test-mcp"]

{
  "mcpServers": {
    "mcp-test-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-test-mcp"],
      "env": {
        "LLM_URL": "https://your-llm-endpoint.com/v1",
        "LLM_MODEL_NAME": "your-model-name",
        "LLM_API_KEY": "your-api-key"
      }
    }
  }
}

[mcp_servers.mcp-test-mcp]
command = "npx"
args = ["-y", "mcp-test-mcp"]

[mcp_servers.mcp-test-mcp.env]
LLM_URL = "https://your-llm-endpoint.com/v1"
LLM_MODEL_NAME = "your-model-name"
LLM_API_KEY = "your-api-key"

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install from PyPI
pip install mcp-test-mcp

# Or install from source
git clone https://github.com/example/mcp-test-mcp
cd mcp-test-mcp
pip install -e ".[dev]"

Command Line Options

The server supports multiple transports for different deployment scenarios:

# Default: stdio transport (for Claude Desktop/Code)
mcp-test-mcp

# Explicit stdio
mcp-test-mcp --transport stdio

# HTTP transport for web deployments
mcp-test-mcp --transport streamable-http
mcp-test-mcp --transport streamable-http --host 0.0.0.0 --port 8080

# Legacy SSE transport (for backward compatibility)
mcp-test-mcp --transport sse --port 9000

Options:

Using with npx:

# HTTP server via npx
npx -y mcp-test-mcp --transport streamable-http --port 8080

Quick Start

Once configured, test MCP servers through natural conversation:

• Connect: "Connect to my MCP server at /path/to/server"
• Connect with auth: "Connect to https://api.example.com/mcp with headers Authorization: Bearer my-token"
• Discover: "What tools does it have?"
• Test: "Call the echo tool with message 'Hello'"
• Status: "What's the connection status?"
• Disconnect: "Disconnect from the server"

Available Tools

Connection Management

• connect_to_server: Connect to a target MCP server (stdio or HTTP). Supports optional headers parameter for authenticated HTTP connections (e.g., {"Authorization": "Bearer token"}). Headers are ignored for stdio transport.
• disconnect: Close active connection
• get_connection_status: Check connection state and statistics

Tool Testing

• list_tools: Get all tools with complete schemas
• call_tool: Execute a tool with arguments

Resource Testing

• list_resources: Get all resources with metadata
• read_resource: Read resource content by URI

Prompt Testing

• list_prompts: Get all prompts with argument schemas
• get_prompt: Get rendered prompt with arguments
• execute_prompt_with_llm: Execute prompts with actual LLM inference

Utility

• health_check: Verify server is running
• ping: Test connectivity (returns "pong")
• echo: Echo a message back
• add: Add two numbers

Environment Variables

Transport Configuration

These environment variables configure the server transport. CLI arguments take precedence.

Priority: CLI argument > environment variable > default

Core

• MCP_TEST_LOG_LEVEL: Logging level (DEBUG, INFO, WARNING, ERROR). Default: INFO
• MCP_TEST_CONNECT_TIMEOUT: Connection timeout in seconds. Default: 30.0

LLM Integration (for execute_prompt_with_llm)

• LLM_URL: LLM API endpoint URL
• LLM_MODEL_NAME: Model name
• LLM_API_KEY: API key

Development

# Install dev dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run with coverage
pytest --cov=mcp_test_mcp --cov-report=html

# Format and lint
black src/ tests/
ruff check src/ tests/
mypy src/

Container Deployment

For deploying mcp-test-mcp in containers (e.g., OpenShift, Kubernetes):

FROM registry.redhat.io/ubi9/python-311:latest

WORKDIR /app

# Install mcp-test-mcp
RUN pip install --no-cache-dir mcp-test-mcp

# Expose HTTP port
EXPOSE 8000

# Run with streamable-http transport
CMD ["mcp-test-mcp", "--transport", "streamable-http", "--host", "0.0.0.0", "--port", "8000"]

Or use environment variables:

# kubernetes deployment snippet
env:
  - name: MCP_TEST_TRANSPORT
    value: "streamable-http"
  - name: MCP_TEST_HOST
    value: "0.0.0.0"
  - name: MCP_TEST_PORT
    value: "8000"

Documentation

• - Complete guide with LLM integration examples

License

MIT License - see for details.

Resources

• FastMCP Documentation
• Model Context Protocol Specification
• Cursor MCP Documentation
• Windsurf MCP Documentation
• VS Code MCP Documentation
• Codex MCP Documentation