Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@my-mcp-server say hello to John"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A starter template for building MCP (Model Context Protocol) servers in TypeScript
A working MCP server with an example hello tool
TypeScript with ES modules
Testing with Vitest
Linting (ESLint) and formatting (Prettier)
CI pipeline and npm publishing workflow
VS Code, Claude Desktop, and Cursor configuration examples
┌─────────────────┐ ┌────────────┐ ┌──────────────────┐
│ AI Assistant │────▶│ MCP Client │────▶│ Your MCP Server │
│ (Copilot/Claude) │◀────│ │◀────│ │
└─────────────────┘ └────────────┘ └──────────────────┘Related MCP server: MCP Server Starter (TypeScript)
npx -y degit matracey/mcp-server-template my-mcp-server
cd my-mcp-server
npm installUpdate name, description, and bin in package.json
Replace the example hello tool in src/server.ts with your own tools
Update the server name/version in src/server.ts
npm run build
npm testnpm run dev # Run with auto-restart on file changes
npm start # Run the built versionEdit src/server.ts and register a new tool:
server.tool(
'my_tool',
'Description of what this tool does.',
{
param: z.string().describe('Parameter description'),
},
async ({ param }) => {
return {
content: [{ type: 'text' as const, text: `Result: ${param}` }],
}
}
)The template includes an example hello tool to demonstrate the pattern.
Once published (or running locally), configure your AI client:
Add to .vscode/mcp.json:
{
"servers": {
"my-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "my-mcp-server"]
}
}
}Add to claude_desktop_config.json:
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["-y", "my-mcp-server"]
}
}
}Add to .cursor/mcp.json:
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["-y", "my-mcp-server"]
}
}
}Replace
my-mcp-serverwith your published package name.
src/
├── index.ts # Entry point — stdio transport setup
├── server.ts # MCP server & tool definitions
├── __tests__/ # Tests (vitest)
└── data/ # Static data (if needed)
scripts/ # Dev-time scriptsNode.js >= 20
npm
npm run build # TypeScript compilation
npm test # Run tests
npm run test:watch # Watch mode
npm run test:coverage # With coverage report
npm run dev # Run with auto-restart on changes
npm run validate # Run all CI checks (format, lint, build, test)Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
MIT — see LICENSE for details.
A simple greeting tool that returns a hello message.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Name to greet |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions 'returns a hello message', implying a read-only operation, but doesn't disclose any behavioral traits like error handling, rate limits, or response format. This leaves the agent with minimal context beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without any wasted words. It is appropriately sized and front-loaded, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter, no annotations, no output schema), the description is minimally adequate. It covers the basic purpose but lacks details on usage, behavior, or output, leaving gaps that could hinder an agent's ability to use it effectively in varied contexts.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the parameter 'name' documented as 'Name to greet'. The description doesn't add any meaning beyond this, such as format constraints or examples. With high schema coverage, the baseline is 3, as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'returns a hello message' with the verb 'returns' and resource 'hello message', making it specific. However, with no sibling tools, it cannot distinguish from alternatives, so it doesn't reach the highest score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or context. It only states what it does, not when or why to invoke it, which is a significant gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0helloWith only one tool, there is no possibility of confusion or overlap between tools, as there are no other tools to disambiguate from. The tool's purpose is clearly distinct by default in this minimal set.
A single tool inherently has perfect naming consistency, as there are no other tool names to compare against or create patterns with. The name 'hello' is straightforward and follows a simple verb-like convention without deviation.
A single tool is generally too few for most server purposes, as it offers very limited functionality and scope, making it feel thin and inadequate for handling typical tasks or workflows in a domain. This server appears to be a trivial example rather than a practical toolset.
The server's purpose is unclear from the single tool, but for any inferred domain (e.g., greeting or basic interaction), the surface is severely incomplete—it lacks any CRUD operations, lifecycle coverage, or meaningful workflows, making it impossible for agents to perform substantive tasks.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server for building and testing AI agents with multi-model experimentation and insights.
Kickstart development with a customizable TypeScript template featuring sample tools for greeting,…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/matracey/mcp-server-template'
If you have feedback or need assistance with the MCP directory API, please join our Discord server