test
test for mcp server
claude mcp add --transport stdio naomori-test-mcp-server node server.js \ --env PORT="3000" \ --env MCP_LOG_LEVEL="info"
How to use
This MCP server implements the MCP (Model Context Protocol) using the command transport format. Commands are sent as JSON objects that specify a command name and its arguments. In this server, three example commands are shown: calculate, calculator, and getImage. Each command is represented by an object with a name field and an arguments field. For example, { "name": "calculate", "arguments": { "operation": "add", "x": 3, "y": 5 } } would trigger a calculation operation. The calculator command takes an expression as a string, e.g., { "name": "calculator", "arguments": { "expression": "3+5" } }. The getImage command takes no arguments, e.g., { "name": "getImage", "arguments": {} }. To use the server, start it with the specified command (in this case, run node server.js). Then connect a client that can send JSON messages over the MCP transport (such as a WebSocket or TCP connection, depending on the server’s implementation) and emit the command objects shown in the examples. Responses will typically be JSON objects indicating results or status for each command.
How to install
Prerequisites:
- Node.js installed on your system (recommended since the server is started with node).
- Basic knowledge of running Node.js applications in the project directory.
Step-by-step:
- Clone or download the MCP Command Server repository.
- Open a terminal and navigate to the project directory.
- Install dependencies (if a package.json exists):
- npm install
- Start the MCP server:
- npm run start or
- node server.js
- Ensure the server is listening on the configured port (default 3000 as per the environment variable in mcp_config).
- Connect a client that can send MCP command messages in JSON format to the server and begin issuing commands such as the examples provided (calculate, calculator, getImage).
Additional notes
Tips:
- The server examples show commands named calculate, calculator, and getImage. Ensure your client uses the same JSON structure: { "name": "<command-name>", "arguments": { ... } }.
- If you modify the port via PORT environmental variable, update your client accordingly.
- If using logs for debugging, set MCP_LOG_LEVEL to debug for verbose output.
- The documentation examples use no authentication; if you expose the server publicly, consider adding auth or network restrictions.
- If you encounter JSON parse errors, verify that the client sends valid JSON with proper escaping and no trailing commas.
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go