Skip to main content
Glama
deenesjakoruzh
mar-co-za

Mnevis MCP Server

by mar-co-za
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Servidor MCP Mnevis

⚠️ Esto es un experimento.

Un servidor MCP de Python ligero, sin dependencias que expone una única herramienta do_everything. Cualquier agente de IA que soporte MCP puede usarlo para delegar todo el trabajo de lenguaje a un endpoint local compatible con OpenAI.

Cómo funciona

AI Agent
    │
    │  MCP stdio (JSON-RPC 2.0)
    ▼
mnevis  server.py
    │
    │  HTTP POST /v1/chat/completions
    ▼
Local LLM  (Ollama, LM Studio, llama.cpp, vLLM, …)

El agente llama a la herramienta do_everything con un prompt (y opcionalmente una instrucción system).
El servidor reenvía la solicitud al LLM local usando la API estándar de chat-completions de OpenAI
y devuelve la respuesta del modelo al agente.

La descripción de la herramienta está redactada para que cualquier LLM entienda automáticamente que debe delegar
cada tarea a la herramienta en lugar de razonar por sí mismo.

Related MCP server: MCP-123

Requisitos

  • Python 3.11+

  • Sin paquetes de terceros — usa solo la biblioteca estándar (urllib, json, sys, os)

  • Un LLM local en ejecución que exponga un endpoint /v1/chat/completions

Configuración

Todos los ajustes se leen de variables de entorno al inicio:

Variable

Valor por defecto

Descripción

MNEVIS_URL

http://localhost

URL base del servidor LLM local

MNEVIS_PORT

11434

Puerto en el que escucha el servidor LLM

MNEVIS_MODEL

llama3

Nombre del modelo a enviar en la solicitud

MNEVIS_API_KEY

(vacío)

Clave API opcional (se envía como token Bearer)

MNEVIS_TIMEOUT

120

Tiempo de espera en segundos para la llamada HTTP al LLM

MNEVIS_LOGLEVEL

INFO

Nivel de registro para diagnósticos del servidor (DEBUG, INFO, WARNING, ERROR)

Ejemplos

Ollama (puerto por defecto 11434):

MNEVIS_MODEL=llama3 python server.py

LM Studio (puerto por defecto 1234):

MNEVIS_URL=http://localhost MNEVIS_PORT=1234 MNEVIS_MODEL=lmstudio-community/Meta-Llama-3-8B-Instruct python server.py

vLLM con clave API:

MNEVIS_URL=http://my-gpu-box MNEVIS_PORT=8000 MNEVIS_MODEL=mistral-7b MNEVIS_API_KEY=secret python server.py

Ejecutar el servidor

El servidor se comunica a través de stdio (JSON-RPC 2.0), por lo que es lanzado como proceso hijo por el host MCP — normalmente no lo ejecutas manualmente.

Para probarlo directamente:

python server.py

Luego pega un mensaje JSON-RPC en bruto, por ejemplo:

{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"0.0.1"}}}

Registrar con un host MCP

Añade a tu mcp.json (del espacio de trabajo o global):

{
  "mcpServers": {
    "mnevis": {
      "command": "python",
      "args": ["/absolute/path/to/mnevis-mcp/server.py"],
      "env": {
        "MNEVIS_URL":   "http://localhost",
        "MNEVIS_PORT":  "11434",
        "MNEVIS_MODEL": "llama3",
        "MNEVIS_API_KEY": ""
      }
    }
  }
}

Para VSCode:

{
  "servers": {
    "mnevis": {
      "command": "python",
      "args": ["/absolute/path/to/mnevis-mcp/server.py"],
      "env": {
        "MNEVIS_URL":   "http://localhost",
        "MNEVIS_PORT":  "11434",
        "MNEVIS_MODEL": "llama3",
        "MNEVIS_API_KEY": ""
      }
    }
  }
}

Reemplaza la ruta args con la ruta absoluta real en tu máquina.
Configura MNEVIS_PORT / MNEVIS_MODEL para que coincidan con tu configuración LLM local.

Herramienta expuesta

do_everything

Argumento

Tipo

Obligatorio

Descripción

prompt

string

✅

La tarea, pregunta o conversación completa a procesar

system

string

❌

Instrucción opcional de sistema/persona para el LLM local

La descripción de la herramienta indica explícitamente al agente llamante que envíe cada tarea aquí en lugar de razonar por sí mismo.

health_check

Argumento

Tipo

Obligatorio

Descripción

(ninguno)

—

—

Devuelve una cadena de estado corta que contiene la versión del servidor, el nombre del modelo configurado, la URL/puerto y el tiempo de espera de la solicitud. Útil para monitorización o depuración.

Solicitud de ejemplo

{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"health_check","arguments":{}}}

Respuesta de ejemplo

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "content": [{"type": "text", "text": "mnevis version 1.0.0 | model=llama3 | url=http://localhost:11434 | timeout=120s"}],
    "isError": false
  }
}

Estructura del proyecto

mnevis-mcp/
├── server.py        # MCP server (single file, stdlib only)
├── pyproject.toml   # Project metadata
├── README.md        # This file
└── .gitignore

Licencia

MIT

Available Tools

1 tool
do_everythingA

Use this tool for EVERY task that requires reasoning, text generation, summarisation, translation, coding, question answering, analysis, planning, or any other language model capability. Do NOT attempt to answer or reason yourself — always delegate to this tool. Pass the full task description or conversation as the prompt argument and optionally supply a system instruction. The tool forwards the request to a local LLM and returns the response.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesThe complete task, question, or conversation turn to process. Include all context the model needs.
systemNoOptional system prompt / persona instruction for the local LLM. Leave blank to use no system message.

TDQS

A3.7/5.0
Behavior2/5

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

No annotations provided, so description carries full burden. Only states it forwards to a local LLM and returns response, lacking details on failure modes, latency, or read-only nature.

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?

Concise, front-loaded, and wastes no words. Every sentence adds value.

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

Completeness4/5

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

Covers core usage and operation adequately for a simple tool with 2 params and no output schema. Could mention return format but sufficient.

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?

Schema coverage is 100%, and description adds meaningful guidance for 'prompt' (include all context) and 'system' (optional persona), slightly above baseline.

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 tool forwards tasks to a local LLM, covering many capabilities. It is specific (forward to LLM) but overly broad ('EVERY task'), which is fine given no siblings.

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

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to always use this tool for reasoning tasks and not to answer directly. Provides clear context with no exclusions, sufficient given no alternatives.

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. 1 tool updatev1.0.0
    • First observeddo_everything
Deploy Server
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

A4/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusing it with other tools. The tool's purpose is clearly stated.

Naming Consistency5/5

With a single tool, naming consistency is inherently perfect. The name 'do_everything' clearly describes its intended use.

Tool Count4/5

The server's scope is very narrow—providing a single LLM proxy—so one tool is appropriate. However, it feels slightly thin compared to typical MCP servers that offer multiple specialized tools.

Completeness5/5

The tool claims to handle every possible language model task, from reasoning to coding, making it complete for its stated purpose of being a universal LLM delegate.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers