MCP Server Boilerplate

@takunagai

About MCP Server Boilerplate

Model Context Protocol(MCP) サーバーのボイラープレートとなるシンプルな実装です。

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-boilerplate-takunagai": {
      "command": "npx",
      "args": [
        "serve",
        "dummy-server"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Server Boilerplate?

MCP Server Boilerplate is a minimal reference implementation of a Model Context Protocol (MCP) server. It provides a starting point for developers to quickly build custom MCP servers and add their own tools, with examples demonstrating implementation patterns.

How to use MCP Server Boilerplate?

Clone the repository, run npm install and npm build, then add the server configuration to your MCP client's settings file using the absolute path to build/index.js. Optionally set environment variables under the "env" key, and start the dummy server with npx serve dummy-server. Restart the MCP client and run one of the provided prompt examples to verify the tools work.

Key features of MCP Server Boilerplate

Two sample tools: double_number and get_test_text
Demonstrates custom tool creation using the MCP SDK
Includes a dummy data server for testing
Multiple version branches showing progressive features
Uses Biomes for linting and formatting

Use cases of MCP Server Boilerplate

Learning how to build and extend an MCP server
Rapidly prototyping custom MCP tools
Testing MCP client integration with a simple server

FAQ from MCP Server Boilerplate

What tools does the boilerplate include?

It includes double_number (doubles a given number) and get_test_text (fetches a string from the dummy server and displays the environment variable FOO).

How do I add a new custom tool?

Edit src/index.ts and follow the documented pattern: define the tool name, description, parameter schema with Zod, and a handler returning a CallToolResult.

What are the runtime requirements?

Node.js v23.11.0 or later, plus npm or yarn.

How do I set environment variables for the server?

Add an "env" object in the MCP client configuration file under the server entry, e.g., "env": { "FOO": "BAR" }.

Which MCP clients are supported?

Claude Code, VSCode, Windsurf, and Cursor are listed; AWS Bedrock is mentioned as untested.

Frequently asked questions

What tools does the boilerplate include?

It includes `double_number` (doubles a given number) and `get_test_text` (fetches a string from the dummy server and displays the environment variable FOO).

How do I add a new custom tool?

Edit `src/index.ts` and follow the documented pattern: define the tool name, description, parameter schema with Zod, and a handler returning a `CallToolResult`.

What are the runtime requirements?

Node.js v23.11.0 or later, plus npm or yarn.

How do I set environment variables for the server?

Add an `"env"` object in the MCP client configuration file under the server entry, e.g., `"env": { "FOO": "BAR" }`.

Which MCP clients are supported?

Claude Code, VSCode, Windsurf, and Cursor are listed; AWS Bedrock is mentioned as untested.

Comments

Basic information

More Developer Tools MCP servers

endoflife.ai

Free MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 485 tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or

TaskerArmy Agent

TaskerArmy

Ask Claude or ChatGPT what Shopify theme optimization tasks are pending on your store, a remote MCP server for TaskerArmy Agent accounts.

Serena

oraios

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

26.2K

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Reelier

Maxime Houle

Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.