Click on "Deploy 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., "@MCP Echo Starter Please echo back: Hello from MCP!"
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.
Minimal Model Context Protocol server in TypeScript: one echo tool over stdio. Use it as a hello-world before building real tools.
Node.js 18+
Related MCP server: mcp-server-starter
npm install
npm test
npm startClaude Code
claude mcp add echo -- node /absolute/path/to/mcp-echo-starter/dist/index.jsCursor — add to MCP settings:
{
"mcpServers": {
"echo": {
"command": "node",
"args": ["/absolute/path/to/mcp-echo-starter/dist/index.js"]
}
}
}Then ask the model to call the echo tool.
This free sample has one tool and a smoke test. The paid MCP Server Starter adds notes CRUD, an SSRF-safe fetch_url, a resource, a prompt template, and a fuller test suite.
Guide: Best MCP Server Starter for TypeScript
MIT
Echo back a short message. Useful as a hello-world MCP tool.
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | Text to echo back |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. 'Echo back' implies a side-effect-free, idempotent read, which is the key behavioral trait, but it never states this explicitly, nor does it describe the return value or any limits beyond the schema's maxLength. Adequate but not rich.
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?
Two short sentences with zero waste; the core action is front-loaded and the second sentence adds useful framing. Nothing is padded.
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?
For a trivial one-parameter tool whose schema fully documents the input, this is nearly complete. The only minor gap is that, absent an output schema, the description never states that the return value is the same message echoed back.
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?
Schema description coverage is 100% and the single 'message' parameter is documented as 'Text to echo back', so the schema does the heavy lifting. The description adds only the informal hint that the message is 'short', aligning loosely with the 500-char cap, so it stays at the baseline.
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?
States a specific verb+resource: 'Echo back a short message.' An agent immediately understands the operation, and there are no siblings to distinguish it from. Slightly loses a point only because 'short message' is informal where a precise scope would be better.
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?
'Useful as a hello-world MCP tool' gives implied usage context — it signals this is a demo/smoke-test tool rather than a production operation. However, it does not state when an agent should prefer this over any other action, nor any exclusions, so the guidance remains implied rather than explicit.
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.
v1.0.0echoScored across 1 tool
There is only one tool, so there is no possibility of misselection or overlap with anything else. Its purpose is unambiguous.
The single tool uses a clear, lowercase verb-style name consistent with MCP conventions. There is no competing convention to conflict with.
One tool is thin even for a server, though the stated purpose is explicitly a hello-world starter where minimalism is intentional. It is borderline rather than a mismatch.
For a demo/starter the surface is self-contained with no dead ends, but there is no domain to cover, so it cannot demonstrate real completeness. It is adequate for its declared demo purpose only.
A Model Context Protocol server for Wix AI tools
Connect AI agents to Replynodes over the Model Context Protocol.
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Hosted MCP runtime where your agent publishes its own tools by tool call and keeps working.
