Skip to main content
Glama
deenesjakoruzh
mar-co-za

Mnevis MCP Server

by mar-co-za
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Mnevis MCP Server

⚠️ Dies ist ein Experiment.

Ein leichtgewichtiger, abhängigkeitsfreier Python-MCP-Server, der ein einziges do_everything-Tool bereitstellt. Jeder KI-Agent, der MCP unterstützt, kann ihn nutzen, um sämtliche Sprachmodell-Arbeit an einen lokalen, OpenAI-kompatiblen Endpunkt auszulagern.

Funktionsweise

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

Der Agent ruft das do_everything-Tool mit einem prompt (und optional einer system-Anweisung) auf.
Der Server leitet die Anfrage unter Verwendung der standardmäßigen OpenAI-Chat-Completions-API an das lokale LLM weiter
und gibt die Antwort des Modells an den Agenten zurück.

Die Tool-Beschreibung ist so formuliert, dass jedes LLM automatisch versteht, dass es jede Aufgabe an das Tool delegieren sollte, anstatt selbst zu schlussfolgern.

Related MCP server: MCP-123

Voraussetzungen

  • Python 3.11+

  • Keine Drittanbieter-Pakete — verwendet nur die Standardbibliothek (urllib, json, sys, os)

  • Ein laufendes lokales LLM, das einen /v1/chat/completions-Endpunkt bereitstellt

Konfiguration

Alle Einstellungen werden beim Start aus Umgebungsvariablen gelesen:

Variable

Standard

Beschreibung

MNEVIS_URL

http://localhost

Basis-URL des lokalen LLM-Servers

MNEVIS_PORT

11434

Port, auf dem der LLM-Server lauscht

MNEVIS_MODEL

llama3

Modellname, der in der Anfrage übergeben wird

MNEVIS_API_KEY

(leer)

Optionaler API-Schlüssel (wird als Bearer-Token gesendet)

MNEVIS_TIMEOUT

120

Anfragetimeout in Sekunden für den LLM-HTTP-Aufruf

MNEVIS_LOGLEVEL

INFO

Protokollierungsstufe für Serverdiagnose (DEBUG, INFO, WARNING, ERROR)

Beispiele

Ollama (Standard-Port 11434):

MNEVIS_MODEL=llama3 python server.py

LM Studio (Standard-Port 1234):

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

vLLM mit API-Schlüssel:

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

Server ausführen

Der Server kommuniziert über stdio (JSON-RPC 2.0), daher wird er als untergeordneter Prozess vom MCP-Host gestartet — in den meisten Fällen führen Sie ihn nicht manuell aus.

Zum direkten Testen:

python server.py

Fügen Sie dann eine rohe JSON-RPC-Nachricht ein, z.B.:

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

Bei einem MCP-Host registrieren

Fügen Sie zu Ihrer mcp.json (Arbeitsbereich oder global) hinzu:

{
  "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": ""
      }
    }
  }
}

Für 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": ""
      }
    }
  }
}

Ersetzen Sie den args-Pfad durch den tatsächlichen absoluten Pfad auf Ihrem Rechner.
Setzen Sie MNEVIS_PORT / MNEVIS_MODEL entsprechend Ihrer lokalen LLM-Konfiguration.

Bereitgestellte Tools

do_everything

Argument

Typ

Erforderlich

Beschreibung

prompt

string

✅

Die vollständige Aufgabe, Frage oder Konversation

system

string

❌

Optionale System-/Persona-Anweisung für das lokale LLM

Die Tool-Beschreibung weist den aufrufenden Agenten explizit an, jede Aufgabe hierher zu senden, anstatt selbst zu schlussfolgern.

health_check

Argument

Typ

Erforderlich

Beschreibung

(keine)

—

—

Gibt einen kurzen Status-String mit der Serverversion, dem konfigurierten Modellnamen, der URL/dem Port und dem Anfragetimeout zurück. Nützlich für Überwachung oder Fehlersuche.

Beispielanfrage

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

Beispielantwort

{
  "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
  }
}

Projektstruktur

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

Lizenz

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