About Mcp Server Basic Sample
Mcp Server Basic Sample is a TypeScript-based example project for building and running an MCP server. It demonstrates setup, inspection, and configuration for use with Claude for Desktop.
Key features
- 01Install dependencies with pnpm
- 02Build the server with pnpm
- 03Run with the MCP Inspector
- 04Configure Claude for Desktop
Use cases
- 01Learn the basic MCP server setup
- 02Inspect a locally running server
- 03Connect a sample server to Claude for Desktop
MCP support
It is a sample MCP server project. The README shows running it with the MCP Inspector and registering it in Claude for Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMcp Server Basic Sample
Prepare mcp server app
1. Install packages
pnpm install
2. Build
pnpm build
Mcp Inspector
Inspector - Model Context Protocol
pnpm start
pnpm inspect
Claude for Desktop
Download Claude for Desktop
Set Configure Claude for Desktop
Open the config file in VSCode.
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
/Users/[user]/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"RandomNumber": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/PARENT/FOLDER/build/index.js"]
}
}
}
If you use mise.
$ mise which node
/Users/[user]/.local/share/mise/installs/node/22.14.0/bin/node
/Users/[user]/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"RandomNumber": {
"command": "/Users/[user]/.local/share/mise/installs/node/22.14.0/bin/node",
"args": ["/ABSOLUTE/PATH/TO/PARENT/FOLDER/build/index.js"]
}
}
}
reference: https://github.com/modelcontextprotocol/servers/issues/64#issuecomment-2503152420
Resources
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.