MCP Starter Server
MCP Starter Server
A minimal ModelContextProtocol server template for building AI assistant tools. This starter provides a basic structure for creating MCP tools that can be used with AI assistants like Claude.
Features
- Simple "hello world" tool example
- TypeScript + esbuild setup
- Development tools preconfigured
Setup to build and run with Claude
- Download and install Claude desktop app from claude.ai/download
- Clone the repo, install dependencies and build:
- Configure Claude to use this MCP server. If this is your first MCP server, in the root of this project run:
This should result in an entry in your claude_desktop_config.json
like:
If you have existing MCP servers, add the mcp-starter
block to your existing config. It's an important detail that the args
is the path to <path_to_repo_on_your_machine>/mcp-starter/dist/index.cjs
.
- Restart Claude Desktop.
- Look for the hammer icon with the number of available tools in Claude's interface to confirm the server is running.
- If this is all working, you should be able to develop your MCP server using
npm run dev
and test it in Claude. You'll need to restart Claude each time to restart the MCP server.
Developing with Inspector
For development and debugging purposes, you can use the MCP Inspector tool. The Inspector provides a visual interface for testing and monitoring MCP server interactions.
Visit the Inspector documentation for detailed setup instructions.
To test locally with Inspector:
To build on file changes run:
Or run both the watcher and inspector:
Publishing
Once you're ready to distribute your server, it's simple!
- Set up an NPM account.
- Run
npm publish
. This will publish a package using the project name inpackage.json
- Once published, others can install the server with a config entry like:
Available Tools
The server provides:
hello_tool
: A simple example tool that takes a name parameter and returns a greeting
Creating New Tools
To add new tools:
- Define the tool schema in
index.ts
- Add it to the tools array in the
ListToolsRequestSchema
handler - Add the implementation in the
CallToolRequestSchema
handler
See the hello_tool
implementation as an example.
You must be authenticated.
This server provides a minimal template for creating AI assistant tools using the ModelContextProtocol, featuring a simple 'hello world' tool example and development setups for building custom MCP tools.