An MCP middleware that acts as both a server (to Claude) and a client (to servers under test) for testing MCP servers during development.
The MCP Test Client has a dual role:
- It's a server registered with Claude that exposes tools for testing
- It's a client that connects to and tests other MCP servers
┌─────────────┐ ┌───────────────────┐ ┌────────────────┐
│ │ Tools │ │ Client │ │
│ Claude │─────────>│ MCP Test Client │─────────>│ Server Under │
│ │ │ │ │ Test │
└─────────────┘ └───────────────────┘ └────────────────┘
This architecture lets you test MCP servers without registering them directly with Claude.
- Deploy MCP servers to test environments
- Call individual tools with custom arguments
- Run automated test suites
- View server logs
- Test servers before formal registration with Claude
The MCP Test Client is implemented with:
- Process Management: Spawns and manages MCP server processes
- MCP SDK Client: Uses the official MCP SDK to communicate with servers
- Custom Transport: Implements a custom transport for stdio communication
- Test Execution: Runs tests and validates responses
- CLI Interface: Provides an interactive testing interface
The current implementation is Phase 1 of the design plan, with future enhancements planned for Phases 2 and 3.
# Install dependencies
npm install
# Build the TypeScript project
npm run buildThe MCP Test Client is registered with Claude via the claude-mcp-local script. You can use the following tools:
- Deploy a server:
mcp__mcp-test__mcp_test_deploy_server({
name: "my-server",
source_path: "/path/to/server",
env_vars: {
"API_KEY": "${API_KEY}"
}
})- Call a tool on a deployed server:
mcp__mcp-test__mcp_test_call_tool({
server_name: "my-server",
tool_name: "tool_name",
arguments: {
// Tool-specific arguments
}
})- Run tests against a server:
mcp__mcp-test__mcp_test_run_tests({
server_name: "my-server"
})- View server logs:
mcp__mcp-test__mcp_test_get_logs({
server_name: "my-server",
lines: 100
})- List deployed servers:
mcp__mcp-test__mcp_test_list_servers({})- Stop a server:
mcp__mcp-test__mcp_test_stop_server({
server_name: "my-server"
})Run the CLI interface for testing:
# Use npm script
npm run test
# Or run directly
node dist/test-runner.jsThis provides an interactive menu for deploying, testing, and managing MCP servers.
The MCP Test Client supports this workflow:
- Develop an MCP server in the playground directory
- Deploy it to the test environment with MCP Test Client
- Test functionality, call individual tools, and debug issues
- Fix and iterate until the server works correctly
- Migrate the server to mcp-servers/ when ready
- Register with Claude through claude-mcp-local
Planned enhancements include:
- Phase 2: Docker-based container management, comprehensive test suites
- Phase 3: Migration tools, more advanced test validation
See notes/mcp_test_client_design.md for the complete design document.