Skip to main content
Glama
deenesjakoruzh
deadSwank001

Nexus-MCP

by deadSwank001
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Nexus-MCP ( Foundry-Reverse )

Versión de Foundry MCP con ingeniería inversa para funcionar en Ollama

Una alternativa de código abierto totalmente local al Servidor MCP de Azure AI Foundry, impulsada completamente por Ollama. Sin suscripción a Azure, sin claves API, sin necesidad de la nube.

Características

Categoría

Herramientas

Salud

health_check

Gestión de modelos

list_models, get_model_info, pull_model, delete_model, list_running_models, compare_models

Inferencia

generate, chat

Evaluación

evaluate_response, evaluate_agent

Conocimiento / RAG

create_index, list_indexes, add_document, query_knowledge, delete_index

Además de Recursos MCP (ollama://models, ollama://running, ollama://indexes) y Prompts reutilizables (summarize, rag_answer, code_review).

Related MCP server: mcplex

Requisitos

  • Python 3.12+

  • Ollama ejecutándose localmente (ollama serve)

  • uv (recomendado) o pip

Inicio rápido

# 1. Clone
git clone https://github.com/deadSwank001/Foundry-Reverse.git
cd Foundry-Reverse

# 2. Copy and edit configuration
cp .env.example .env

# 3. Run the MCP server (stdio transport)
uv run foundry-reverse

Integración con VS Code / Copilot

Copia mcp.json al archivo .vscode/mcp.json de tu espacio de trabajo de VS Code (o a la configuración de MCP a nivel de usuario), luego reinicia VS Code.

{
  "mcpServers": {
    "foundry-reverse": {
      "command": "uv",
      "args": ["run", "foundry-reverse"],
      "env": {
        "OLLAMA_BASE_URL": "http://localhost:11434"
      }
    }
  }
}

Configuración

Variable

Predeterminado

Descripción

OLLAMA_BASE_URL

http://localhost:11434

Punto de conexión de la API de Ollama

OLLAMA_TIMEOUT

120

Tiempo de espera de la solicitud en segundos

EMBED_MODEL

nomic-embed-text

Modelo de Ollama utilizado para incrustaciones (embeddings)

JUDGE_MODEL

(primero disponible)

Modelo de Ollama utilizado como evaluador

KNOWLEDGE_STORE_PATH

.foundry_knowledge.json

Ruta para el almacén RAG local

Desarrollo

# Install deps (including dev)
uv sync --all-groups

# Run tests
uv run pytest

Arquitectura

src/foundry_reverse/
├── __init__.py          # Package version
├── server.py            # FastMCP server – all tools, resources, prompts
├── ollama_client.py     # Async Ollama REST API client
├── evaluation.py        # LLM-as-judge evaluation helpers
└── knowledge.py         # In-memory vector store (cosine similarity + Ollama embeddings)

Comparación con Azure AI Foundry MCP

Característica

Azure Foundry MCP

Foundry-Reverse

Catálogo de modelos

Registro de modelos de Azure AI

Modelos locales de Ollama

Inferencia

Azure OpenAI / serverless

Ollama (/api/generate, /api/chat)

Incrustaciones

Incrustaciones de Azure OpenAI

Ollama (/api/embeddings)

Búsqueda vectorial

Azure AI Search

Similitud de coseno en memoria

Evaluación

SDK de evaluación de Azure AI

LLM local como juez

Autenticación

Azure Service Principal / claves

Ninguna (solo local)

Coste

Pago por token

Gratuito

Install Server
F
license - not found
B
quality
D
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

View all tools

Related MCP Servers

  • mcplex

    dbhavery
    A
    license
    Not graded
    quality
    Not graded
    maintenance
    An MCP server that bridges local Ollama models and ChromaDB vector memory to MCP clients like Claude Code. It enables local text generation, vision-based image analysis, and semantic memory storage without requiring external API keys.

  • mcp-ollama-python

    pblagoje
    A
    license
    Not graded
    quality
    B
    maintenance
    A Python MCP server that exposes local Ollama models as tools for AI assistants, enabling chat, generation, embeddings, and model management without cloud APIs.
    5
    MIT
  • Local AI MCP by TMHSDigital

    Local AI MCPofficial

    TMHSDigital
    A
    license
    A
    quality
    A
    maintenance
    Unified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.
    16
    224
    Creative Commons Attribution Non Commercial No Derivatives 4.0 International

View all related MCP servers

Related MCP Connectors

  • microservices.sh

    MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • anythingmcp

    Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code.

  • TokenOracle

    Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/deadSwank001/Nexus-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server