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 User Management Server create a new user named John Doe with email john@example.com"
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.
This is a simple user management service built with Node.js, TypeScript, and the Model Context Protocol (MCP).
Node.js
npm
Related MCP server: MCP Test Server
Clone the repository:
git clone <repository-url>Install dependencies:
npm installBuild the project:
npm run server:buildRun the server in development mode:
npm run server:devnpm test: Runs the test suite (currently empty).
npm run server:build: Compiles the TypeScript code to JavaScript.
npm run server:build:watch: Compiles the TypeScript code in watch mode.
npm run server:dev: Runs the server in development mode using tsx.
npm run server:dev:watch: Runs the server in development mode with watch mode enabled.
npm run server:inspect: Inspects the server using the MCP inspector.
.
├── build/ # Compiled JavaScript files
├── node_modules/ # Project dependencies
├── src/ # TypeScript source code
│ ├── data/
│ │ └── users.json # User data
│ └── server.ts # MCP server implementation
├── package.json # Project metadata and dependencies
├── tsconfig.json # TypeScript configuration
└── ...The server exposes the following functionalities through the Model Context Protocol:
get-users (users://all): Retrieves a list of all users.
create-user: Creates a new user with the following parameters:
name (string)
email (string)
password (string)
address (string)
phone (string)
Create a new user
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| Yes | |||
| password | Yes | ||
| address | Yes | ||
| phone | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate this is a non-read-only, non-destructive, non-idempotent, open-world operation. The description adds no behavioral context beyond 'create', such as authentication needs, rate limits, or side effects. It doesn't contradict annotations, but with annotations covering key traits, the description's minimal addition results in a baseline score.
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 extremely concise with a single sentence 'Create a new user', which is front-loaded and wastes no words. It efficiently conveys the core action without unnecessary details, 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 complexity of a user creation tool with 5 required parameters, 0% schema coverage, no output schema, and annotations that don't fully explain behavior (e.g., no auth or error handling), the description is incomplete. It lacks details on parameters, return values, or operational context, making it inadequate for effective tool 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 0%, meaning parameters (name, email, password, address, phone) are undocumented in the schema. The description adds no information about these parameters, such as formats, constraints, or examples, failing to compensate for the lack of schema documentation.
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 'Create a new user' clearly states the verb ('create') and resource ('user'), making the purpose understandable. However, it lacks specificity about what kind of user or system context, and with no sibling tools, it doesn't need differentiation but remains somewhat vague beyond the basic action.
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, such as prerequisites, alternatives, or exclusions. With no sibling tools mentioned, it doesn't address context or comparisons, leaving the agent without usage instructions beyond the obvious action implied by the name.
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.
create-userScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to compare it against. The single tool's purpose is clearly defined and distinct by default.
The single tool name follows a clear verb_noun pattern (create-user), and with only one tool, consistency is inherently perfect as there are no other names to deviate from this pattern.
A server named 'User Management Server' with only one tool (create-user) is severely under-scoped, as user management typically requires at least get, update, delete, and list operations. This single tool feels incomplete and inadequate for the domain.
The tool surface is extremely incomplete for user management, lacking essential operations like retrieving, updating, deleting, or listing users. Agents will be unable to perform basic user management tasks beyond creation, leading to frequent failures.
Model Context Protocol server for Studex tools, notifications, and profile integrations
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
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
A Model Context Protocol (MCP) server for Selise Blocks Cloud integration
