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., "@Test MCP Server Create a random user"
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 Model Context Protocol (MCP) server for managing user data with support for resources, tools, and prompts.
The server provides two resource endpoints for accessing user data:
All Users (users://all) - Retrieves all users from the database
User Profile (users://{userId}/profile) - Retrieves a specific user's profile by ID
Three tools are available for user management:
create-user - Create a new user with specified details
Parameters: name, email, address, phone
create-random-user - Automatically generate and create a user with fake data
Uses AI sampling to generate realistic user information
generate-fake-user (Prompt) - Generate fake user data based on a given name
Parameter: name
Related MCP server: Task MCP Server
npm installNode.js (with ES modules support)
Dependencies:
@modelcontextprotocol/sdk
zod
npm startThe server uses stdio transport for communication.
Get all users:
users://allGet specific user profile:
users://123/profileCreate a user:
{
"name": "John Doe",
"email": "john@example.com",
"address": "123 Main St",
"phone": "555-0123"
}Create a random user: No parameters required - automatically generates fake user data using AI sampling.
User data is stored in ./src/data/users.json as a JSON array. Each user object contains:
id (number) - Auto-incremented user ID
name (string) - User's full name
email (string) - Email address
address (string) - Physical address
phone (string) - Phone number
Resources: Query user data via URI schemes
Tools: Perform user management operations
Prompts: Generate templated prompts for user creation
The server is built using the Model Context Protocol SDK and implements:
Resource templates with dynamic URI parameters
Tool definitions with Zod schema validation
AI sampling for generating fake data
File-based persistence
MIT
User IDs are auto-incremented starting from the current user count + 1
All operations return JSON responses
Error handling is implemented for user not found scenarios
The server uses the sampling API to generate realistic fake user data
Create a random user with fake data
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly=false, destructive=false, and idempotent=false. The description adds that the data is fake, but it does not disclose other behavioral traits such as what side effects occur, whether the user is persisted, or what the return value contains. No contradiction with annotations.
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?
One short, front-loaded sentence communicates the essential purpose without any redundant words or unnecessary detail.
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?
The tool is simple (no parameters), but there is no output schema and the description does not explain what the tool returns (e.g., the generated user's email, password, ID). This leaves a clear gap for an agent trying to use the result.
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 tool has zero parameters, so the baseline for this dimension is 4. The description correctly says nothing about parameters, and the empty input schema is fully consistent.
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 action ('Create'), the resource ('random user'), and the distinguishing characteristic ('with fake data'). This differentiates it from the sibling tool 'create-user', which presumably creates a real or specific user.
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 implies a usage context (generating fake/test data) through the words 'random user with fake data', but it does not explicitly say when to use this tool versus the sibling 'create-user', nor does it mention any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new user in the database
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| Yes | |||
| phone | Yes | ||
| address | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey the safety profile (readOnlyHint false, destructiveHint false, idempotentHint false), and the description only restates the obvious 'create' operation, adding no extra context such as authentication needs, side effects on duplicate emails, or return behavior. This is a missed opportunity to disclose meaningful behavioral traits beyond structured data.
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, front-loaded sentence that states the core purpose without wasted words. It is appropriately concise for a simple tool, though it lacks substance that could be included without becoming verbose.
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 no output schema, four required parameters, and a mutation operation, the description should at least mention what the tool returns upon success, how errors (e.g., duplicate email) are handled, or any required permissions. None of this is present, leaving significant gaps for an agent to make safe and correct calls.
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?
With 0% schema description coverage and no parameter details in the description, the agent receives no semantic information about name, email, address, or phone beyond their obvious string names. The description does not compensate for the schema's silence, failing to explain formats, constraints, or required combinations.
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 in the database' uses a specific verb and resource, clearly indicating a create operation. It does not explicitly differentiate from the sibling tool 'create-random-user', though the meaning is implicitly distinct (this creates a specific user, the sibling creates a random one).
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?
No explicit guidance is provided about when to use this tool versus create-random-user. The description implies a use case for adding a specific user, but it does not state conditions, prerequisites, or mention the alternative, leaving the decision to the agent's inference.
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.
v1.0.0create-random-usercreate-userScored across 2 tools
The two tools are clearly described: one creates a specified user, the other generates a random one. While both involve creation, the random qualifier distinguishes them, so an agent should not easily confuse them.
Both tools follow a consistent verb_noun pattern (create-user, create-random-user), with the second incorporating a modifier while maintaining the same structure. The naming is uniform and predictable.
With only 2 tools, this is a very thin set, but it could be appropriate for a narrowly scoped server focused solely on user creation. It falls into the borderline range (1-2 tools), neither too many nor too few for the apparent purpose.
The server only offers creation capabilities, lacking essential operations like retrieving, updating, or deleting users. This leaves obvious gaps in the user lifecycle, which would cause agent failures if the server is intended for full user management.
Manage portable AI agent playbooks, Agent Skills, MCP configurations, personas, and memory.
Self-hosted AI prompt library: prompts, collections, tags, teams, chains. 29 MCP tools for agents.
Scraps Kitchen gives any AI agent a persistent, household-aware kitchen memory. Unlike generic chatbot recall, Scraps maintains structured cooking data: what's in your fridge (with freshness tracking), who you cook for (with allergens, dietary restrictions, and preferences), your recipe collection (with cook notes and per-diner ratings), your shopping list, and your kitchen equipment. 27 tools across 6 domains let agents read kitchen context, suggest meals that respect dietary safety, update the pantry after cooking, and build a history of what works for your household. Every interaction makes the data richer. Cooking history, preference signals, kitchen awareness = better suggestions next time. All tools work via oAuth and a free scraps.kitchen account.
Read and write a CRM built for agents. Every change carries who asserted it and how.
