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., "@HelloWorld MCP Server hello Alice"
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 simple HelloWorld MCP (Model Context Protocol) server experiment built with TypeScript.
This MCP server provides two simple tools:
hello: Say hello to someone (default: "World")
add: Add two numbers together
Related MCP server: Example MCP Server
Node.js 22+ (LTS)
npm
nvm (recommended for Node.js version management)
direnv (for environment management)
Node.js Version Management
# If you have nvm installed:
nvm use
# This will use Node.js version 22 as specified in .nvmrcEnvironment Setup with direnv
# Allow direnv for this directory
direnv allow
# This will automatically add node_modules/.bin to your PATHInstall Dependencies
npm installnpm run dev - Run the server in development mode using tsx
npm run build - Compile TypeScript to JavaScript
npm start - Run the compiled server
npm run lint - Run ESLint on the source code
npm run lint:fix - Run ESLint and automatically fix issues
npm run clean - Remove the dist directory
For development:
npm run devFor production:
npm run build
npm startThis server communicates via stdio and implements the Model Context Protocol. It provides:
hello
Description: Say hello to someone
Parameters:
name (optional): The name of the person to greet (default: "World")
Example: {"name": "Alice"} → "Hello, Alice! 👋 Welcome to the HelloWorld MCP server!"
add
Description: Add two numbers together
Parameters:
a (required): First number
b (required): Second number
Example: {"a": 5, "b": 3} → "5 + 3 = 8"
├── src/
│ └── index.ts # Main MCP server implementation
├── dist/ # Compiled JavaScript (after build)
├── .nvmrc # Node.js version specification
├── .envrc # direnv configuration
├── eslint.config.js # ESLint configuration
├── tsconfig.json # TypeScript configuration
├── package.json # Node.js project configuration
└── README.md # This fileThis project uses:
TypeScript for type safety
ESLint with TypeScript support for code quality
Strict TypeScript configuration for better type checking
MIT
Add two numbers together
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | First number | |
| b | Yes | Second number |
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 accurately states the core operation but does not explicitly mention the return value (the sum) or any error conditions. For a pure arithmetic operation this is a minor gap, but a strictly higher score would require more explicit behavioral disclosure.
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, tightly worded sentence that wastes no words and front-loads the operation. It is concise and well-structured for a simple tool.
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 two-number arithmetic tool, the description is largely complete: it specifies the operation and the schema defines required inputs. There is no output schema or annotations, but the expected result (the sum) is universally implied. A slightly higher score would require explicit mention of return type or edge cases, which are low-risk here.
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?
Input schema covers both parameters fully (100% coverage) with descriptions for 'a' and 'b'. The tool description adds no parameter-level semantic detail beyond indicating the operation is addition, which is expected. Baseline 3 is appropriate when schema already documents parameters.
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 'Add two numbers together' uses a specific verb (add) and resource (two numbers), clearly distinguishing it from sibling arithmetic tools like subtract, multiply, and divide. An agent can immediately understand what this tool does and how it differs from alternatives.
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 clearly implies the context of use: whenever addition of two numbers is needed. Though it doesn't explicitly enumerate when not to use it versus alternatives, the semantic clarity of 'add' combined with the sibling names makes the choice unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Say hello to someone
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | The name of the person to greet | World |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. 'Say hello to someone' implies a read-only, non-destructive action, but it doesn't specify whether this requires authentication, has rate limits, returns structured data, or how the greeting is delivered (e.g., console output, API response). For a tool with zero annotation coverage, this leaves significant behavioral gaps.
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 with zero wasted words. It's front-loaded with the core purpose and appropriately sized for a simple greeting tool. Every word earns its place without redundancy or unnecessary elaboration.
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 optional parameter, no output schema, no annotations), the description is minimally adequate. It states what the tool does but lacks details on behavioral traits, usage context, or output format. For such a simple tool, this might be sufficient, but it doesn't provide complete guidance for optimal agent use.
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%, with the single parameter 'name' fully documented in the schema as 'The name of the person to greet' with a default value. The description doesn't add any parameter details beyond what the schema provides, so it meets the baseline score of 3 for high schema coverage without extra value.
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 'Say hello to someone' clearly states the tool's purpose with a specific verb ('say hello') and target ('to someone'). It distinguishes from the sibling tool 'add' which likely performs a different function. However, it doesn't specify the exact output format or delivery mechanism, keeping it from a perfect score.
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. It doesn't mention any context, prerequisites, or comparisons with the sibling tool 'add'. The agent must infer usage solely from the tool name and description without explicit direction.
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.
addhelloScored across 2 tools
The two tools have completely distinct purposes: 'add' performs a mathematical operation on numbers, while 'hello' handles a greeting interaction. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.
Both tool names are simple, lowercase verbs ('add' and 'hello') that clearly indicate their actions. While they don't follow a strict verb_noun pattern, the naming is perfectly consistent in style and readability for this minimal set.
With only two tools, this server feels extremely thin and under-scoped for any meaningful domain. The tools are trivial and unrelated, suggesting either a demo/test server or one with significant missing functionality for practical use.
The server lacks a coherent domain, making completeness impossible to assess meaningfully. The tools are isolated operations (math and greeting) with no logical connection or coverage of any workflow, representing a severely incomplete surface for any real-world purpose.
A simple Typescript MCP server built using the official MCP Typescript SDK and smithery/cli. This…
POC MCP server. Tool say_hello returns 'Welcome' (agent -> MCP -> API path).