Skip to main content
Glama
SufyaanKhateeb

User Management MCP Server

by SufyaanKhateeb
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

Model Context Protocol (MCP) Learning Notes

Video Reference

Related MCP server: MCP PostgreSQL Server

What is MCP?

Model Context Protocol (MCP) is a protocol that defines how a client (such as an LLM) can communicate and use tools and resources defined at the server level. It implements a client-server architecture with the following components:

  • Tools

  • Resources

  • Prompts

  • Samplings

Documentation & Resources

Implementation Details

Server Setup

The src/server.ts file contains the code for creating an MCP server and defining tools, resources, and prompts.

Testing the Implementation

  1. Build the server:

    npm run server:build

  2. Add to VS Code using the "Add MCP server" command

  3. Access server functionality in the Copilot chat UI

  4. Use "#" followed by tool name to access implemented tools

Viewing the implemented tools

Client Implementation

Note: to use the query and prompts from the client you will need a gemini ai api key, you can add this in the .env file

The src/client.ts file provides a CLI client for interacting with the MCP server. It connects to the server, lists available tools, resources, and prompts, and allows you to:

  • Query the LLM directly

  • Run tools (with parameter input)

  • Access resources (with dynamic URI parameters)

  • Use prompts (with argument input)

How it works

  1. Connects to the MCP server using a transport layer.

  2. Fetches available tools, resources, prompts, and resource templates.

  3. Presents a menu for the user to select an action: Query, Tools, Resources, or Prompts.

  4. Handles each action:

    • Query: Sends a prompt to the LLM and optionally invokes tools.

    • Tools: Lets you select and run a tool, entering parameters as needed.

    • Resources: Lets you select a resource or template, entering URI parameters if required, and displays the result.

    • Prompts: Lets you select a prompt, enter arguments, and view the generated output.

  5. For prompts, you can choose to run the generated text through the LLM for further results.

Example Usage

When you run the client, you'll see a menu:

What would you like to do
❯ Query
  Tools
  Resources
  Prompts

Selecting an option will guide you through the available features interactively.

Resources

  • users: Retrieves all users from the JSON file

  • user-details: Retrieves user details by ID

Tools

  • create-user: Creates a new user with the following parameters:

    • username

    • email

    • address

    • age

    • phone number

  • create-random-user: Generates and creates a random user

Prompts

  • generate-fake-user: Prompt with fixed fields for generating fake user data

Sampling

  • create-random-user: This uses sampling i.e. calling requests on the LLM or clientto generate something.

Available Tools

2 tools
create-random-userA

Create a random user with fake data

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.9/5.0
Behavior3/5

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.

Conciseness5/5

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.

Completeness3/5

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.

Parameters4/5

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.

Purpose5/5

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.

Usage Guidelines3/5

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-userC

Create a new user in the system

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYes
emailYes
addressYes
ageYes
phoneYes

TDQS

C2.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states 'Create a new user', which aligns with the annotations indicating a write operation (readOnlyHint: false) and non-destructive action (destructiveHint: false). However, it doesn't add meaningful behavioral context beyond what annotations provide, such as authentication requirements, rate limits, or what happens on duplicate entries.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. It's front-loaded with the core purpose and efficiently communicates the basic action without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that creates users with 5 required parameters and no output schema, the description is insufficient. It lacks parameter explanations, usage guidance relative to siblings, and behavioral details not covered by annotations, making it incomplete for effective agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage for 5 required parameters, the description provides no information about what 'name', 'email', 'address', 'age', or 'phone' mean in this context. It fails to compensate for the schema's lack of descriptions, leaving parameters semantically undefined.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create') and resource ('a new user in the system'), making the purpose immediately understandable. However, it doesn't differentiate from its sibling tool 'create-random-user', which appears to serve a similar purpose but with different parameters or behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 its sibling 'create-random-user'. There's no mention of prerequisites, alternatives, or specific contexts where this tool is preferred, leaving the agent without usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updates
    • First observedcreate-random-user
    • First observedcreate-user
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.9/5.0

Scored across 2 tools

Disambiguation1/5

The two tools have highly overlapping purposes: both create users. 'create-random-user' and 'create-user' differ only in the data source (fake vs. system), which is a subtle distinction that agents will likely confuse. This is a classic case of ambiguous tool boundaries.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern with hyphen-separated names. 'create-random-user' and 'create-user' are perfectly aligned in naming style, making them predictable and readable.

Tool Count2/5

With only 2 tools, the server feels severely under-scoped for a 'User Management' domain. A user management system typically requires at least CRUD operations (create, read, update, delete) and possibly list/search tools. This minimal set is inadequate for the implied purpose.

Completeness1/5

The tool surface is extremely incomplete for user management. There are no tools to retrieve, update, delete, or list users, creating significant gaps that will cause agent failures. Agents cannot perform basic user management workflows beyond creation.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP PostgreSQL Server

    a21071
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables performing PostgreSQL database operations (create, read, update, delete) on User and Post entities through MCP tools.
    300
    MIT

  • MCP Test Server

    small-tou
    F
    license
    C
    quality
    D
    maintenance
    A testing server that demonstrates Model Context Protocol features, providing access to user data, todos, and system information through resources, tools for user management and calculations, and prompt templates for various analyses.
    4
    -

  • MCP Test Server

    yvanfreitas
    F
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server that enables LLMs to interact with user and task data through JSON-RPC, offering tools like user management, task creation, and search functionality.
    8
    9
    -