Skip to main content
Glama
deenesjakoruzh
kritikatripathi03

toy-mcp-server

by kritikatripathi03
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

toy-mcp-server

Un servidor mínimo de Model Context Protocol (MCP) construido desde cero para aprender cómo funciona MCP de verdad: sin generadores de boilerplate, sin plantillas, solo el SDK.

Creado como primer proyecto práctico de MCP: dos herramientas y un recurso, conectados a Claude Desktop mediante stdio.

Qué hace

MCP permite que un cliente LLM (como Claude Desktop) llame a funciones que se ejecutan en tu propia máquina, en lugar de limitarse a generar texto a partir de sus datos de entrenamiento. Este servidor expone:

Herramientas (funciones que Claude puede llamar):

  • roll_dice — lanza N dados con un número configurable de caras

  • flip_coin — lanza una moneda al aire N veces

Recursos (datos de solo lectura que Claude puede solicitar):

  • server-info — metadatos básicos del servidor (nombre, propósito, hora de inicio)

Related MCP server: Random-Generator

Por qué existe

Los LLM no pueden acceder a nada más allá de sus propios datos de entrenamiento y, por defecto, no pueden hacer nada: solo generar texto. MCP es una forma estándar de dar al modelo:

  • capacidad que no tiene por sí solo (p. ej. la aleatoriedad real: los LLM son notoriamente malos eligiendo números aleatorios)

  • acceso a datos actualizados, a pool de datos o privados que no tiene manera de conocer

Este proyecto es un sandbox pequeño y seguro para esa idea antes de llevar un servidor MCP a un recurso real (una base de datos, una API con autenticación, etc.)

Tecnologías utilizadas

  • TypeScript

  • @modelcontextprotocol/sdk — SDK oficial de MCP

  • zod — validación de esquemas para los argumentos de las herramientas

  • transporte stdio (comunicación local por subproceso con Claude Desktop)

Estructura del proyecto

toy-mcp-server/
├── src/
│   └── index.ts       # server setup, tools, and resource
├── build/              # compiled output (git-ignored)
├── package.json
├── tsconfig.json
└── README.md

Configurar

1. Instalar los dependencias

npm install

2. Compilar

npm run build

3. Conectar con Claude Desktop

Encuentra el archivo de configuración de Claude Desktop:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: normalmente en %LOCALAPPDATA%\Packages\<Claude package folder>\LocalCache\Roaming\Claude\claude_desktop_config.json; la ruta exacta puede variar según el método de instalación (Microsoft Store en comparación con el instalador directo). La forma fiable de encontrarlo es: abre Claude Desktop → Configuracióndesarrollador → Servidores MCP locales → Editar configuración, que abre el archivo exacto que la aplicación lee.

Añade este servidor bajo mcpServers (combínalo con el archivo existente en lugar de sobrescribirlo):

{
  "mcpServers": {
    "toy-mcp-server": {
      "command": "node",
      "args": ["/absolute/path/to/toy-mcp-server/build/index.js"]
    }
  }
}

Reemplaza la ruta por la ruta absoluta real hasta build/index.js en tu máquina.

Windows: escapa las barras invertidas de la ruta dentro de la cadena JSON.

4. Reiniciar Claude Desktop

Sal de Claude Desktop por completo (no solo cierra la ventana) y vuelve a abrirlo. Ve a ConfiguraciónDesarrollador → Servidores MCP locales para confirmar que toy aparece como conectado. toy-mcp-server aparece como conectado.

5. Prueba y

En un chat, pide por ejemplo:

  • "Tira 3 dados de seis caras"

  • "Lanza una moneda 10 veces"

Deberías ver un pequeño indicador de llamada a la herramienta (por ejemplo, "Roll Dice") junto a la marca final, comprobando que Claude ha invocado la función de verdad en lugar de adivinar la respuesta.

Cómo funciona, en breve

  • McpServer — el objeto que declara las capacidades del servidor ante cualquier cliente que se conecte

  • registerTool(name, config, handler) — registra una función que se puede llamar. config.inputSchema usa Zod para validar los argumentos que el modelo envíe el servidor con el fin de que se ejecute el handler

  • registerResource(name, uri, config, handler) — registra datos de solo lectura más direccionados por una URI, que se recuperan estén eternados sin argumentos

  • StdioServerTransport — la fuente de conexión: Claude Desktop lanza el archivo como un subproceso y se comunica con él a través de stdin/stdout usando JSON-RPC. console.log nunca se usa aquí para registrar, ya que stdout es el canal real del protocolo; en su lugar por defecto se usa console.error (estderr).

Próximos pasos

  • Cambia los webs de juguete por otros reales que conecten con una base de datos real (postgres vía Prisma)

  • Añade una herramienta con respaldo de GitHub (p. ej. list_open_prs) para practicar con autenticación por token

  • Explora una sinta el transporte Streamable HTTP para subir este servidor de forma remota, en lugar de ejecutarlo localmente

Licencia

MIT

Available Tools

2 tools
flip_coinFlip CoinB

Flip a coin one or more times

NameRequiredDescriptionDefault
timesNoNumber of flips

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of disclosing behavior. It merely says 'Flip a coin one or more times' without mentioning that the outcome is random, what the return format is (e.g., 'heads'/'tails'), or any side effects. The agent is left to guess the result structure.

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, efficient sentence that states the action and the parameter scope. There is zero wasted text, and the core information is front-loaded. It is appropriately concise for a trivial tool.

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?

Given there is no output schema, the description should explain what the tool returns (e.g., results of each flip). It omits any mention of return values or randomness, leaving the agent with incomplete information to use the tool correctly. For a tool this simple, more context is still needed.

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

Parameters3/5

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

The single parameter 'times' is fully described in the schema ('Number of flips'), covering 100% of parameters. The tool description repeats the concept ('one or more times') but adds no extra meaning beyond what the schema already provides, so the baseline score of 3 applies.

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 states a specific verb and resource ('Flip a coin') and adds the scope 'one or more times', which distinguishes it from the sibling roll_dice by naming the object of the action. An agent can clearly identify what this tool does.

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?

No guidance is given about when to use this tool versus roll_dice. The description only states the action, leaving the agent to infer from the name that this is for coins rather than dice. No exclusions, prerequisites, or alternative-routing hints are provided.

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

roll_diceRoll DiceB

Roll one or more dice with a given number of sides

NameRequiredDescriptionDefault
countNoNumber of dice to roll
sidesNoNumber of sides per die

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It does not mention that the result is random, that it is a safe non-mutating operation, or any other behavioral trait beyond the literal act of rolling. This is a significant gap for a tool whose entire purpose is random generation.

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

Conciseness4/5

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

The description is a single concise sentence with no waste. The core action is front-loaded. It is appropriately sized for a tool with only two parameters, though it could have been slightly more informative without losing conciseness.

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?

For a simple tool with two parameters fully documented in the schema, the description is reasonably complete. However, the lack of any mention of randomness or return behavior (even though no output schema is provided) leaves a small but notable gap. An agent might not know the outcome is random without prior knowledge.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents both parameters (count and sides) with defaults, minimums, and maximums. The description adds no semantic meaning beyond what the schema provides, which meets the baseline of 3.

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 states exactly what the tool does: 'Roll one or more dice with a given number of sides'. It uses a specific verb (roll) and resource (dice), and clearly distinguishes from the sibling flip_coin, since dice and coins are different objects.

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?

No guidance on when to use this tool versus the sibling flip_coin. The context implies dice vs coin, but the description does not explicitly state that this is for dice and flip_coin is for coins, nor does it mention any exclusions or alternative conditions.

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 updatesv1.0.0
    • First observedflip_coin
    • First observedroll_dice
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 2 tools

Disambiguation5/5

The two tools, roll_dice and flip_coin, are completely distinct in their purpose and behavior. There is no overlap or ambiguity, making it trivial for an agent to select the correct tool.

Naming Consistency5/5

Both tool names follow the same verb_noun pattern (roll_dice, flip_coin), using snake_case and clear action-object structure. This is perfectly consistent and predictable.

Tool Count4/5

With only 2 tools, the server is minimal, but given its explicit 'toy' purpose and narrow domain (random chance events), this count is appropriate and focused. It is slightly thin by general standards but well-scoped for a toy.

Completeness4/5

The tool surface covers the two most common random generators (dice and coin flips). While a generic random number generator or card draw might be expected in a broader utilities server, for a toy server focused on simple chance, these tools are sufficient and leave no obvious dead ends.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Random Number MCP

    zazencodes
    A
    license
    A
    quality
    C
    maintenance
    Production-ready MCP server that provides LLMs with essential random generation abilities, including random integers, floats, choices, shuffling, and cryptographically secure tokens.
    7
    57 PyPI
    51
    MIT

  • Random-Generator

    xiaobenyang-com
    A
    license
    A
    quality
    D
    maintenance
    An encrypted and secure random number generation server that complies with the MCP protocol, suitable for AI applications, LLMS, and other systems that require high-quality random numbers.
    7
    2
    Apache 2.0

  • mcp-tools-server

    RenanMiqueloti
    A
    license
    Not graded
    quality
    D
    maintenance
    A general-purpose MCP server with utility tools including datetime information, safe math calculations, text statistics, JSON extraction, knowledge base search, and HTTP GET requests. It demonstrates server-side MCP implementation and can be connected to Claude Desktop or LangGraph agents.
    MIT

  • mcp-random

    MikeyBeez
    A
    license
    A
    quality
    C
    maintenance
    MCP server providing true randomness capabilities to Claude, enabling cryptographically secure random number generation for games, decision-making, sampling, simulations, and any operation requiring genuine randomness.
    13
    2
    MIT