Skip to main content
Glama

Nexus-MCP ( Foundry-Reverse )

针对 Ollama 逆向工程优化的新型 Foundry MCP


这是 Azure AI Foundry MCP Server 的一个完全本地、开源的替代方案,完全由 Ollama 驱动。 无需 Azure 订阅,无需 API 密钥,无需云端支持。

功能特性

类别

工具

健康检查

health_check

模型管理

list_models, get_model_info, pull_model, delete_model, list_running_models, compare_models

推理

generate, chat

评估

evaluate_response, evaluate_agent

知识库 / RAG

create_index, list_indexes, add_document, query_knowledge, delete_index

此外还包含 MCP 资源 (ollama://models, ollama://running, ollama://indexes) 和可重用的 提示词 (summarize, rag_answer, code_review)。

Related MCP server: mcplex

要求

  • Python 3.12+

  • 本地运行的 Ollama (ollama serve)

  • uv (推荐) 或 pip

快速开始

# 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

VS Code / Copilot 集成

mcp.json 复制到你的 VS Code 工作区 .vscode/mcp.json(或用户级 MCP 配置),然后重启 VS Code。

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

配置

变量

默认值

描述

OLLAMA_BASE_URL

http://localhost:11434

Ollama API 端点

OLLAMA_TIMEOUT

120

请求超时时间(秒)

EMBED_MODEL

nomic-embed-text

用于嵌入的 Ollama 模型

JUDGE_MODEL

(第一个可用模型)

用作评估器的 Ollama 模型

KNOWLEDGE_STORE_PATH

.foundry_knowledge.json

本地 RAG 存储路径

开发

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

# Run tests
uv run pytest

架构

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)

与 Azure AI Foundry MCP 的对比

特性

Azure Foundry MCP

Foundry-Reverse

模型目录

Azure AI 模型注册表

本地 Ollama 模型

推理

Azure OpenAI / 无服务器

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

嵌入

Azure OpenAI 嵌入

Ollama (/api/embeddings)

向量搜索

Azure AI Search

内存余弦相似度

评估

Azure AI Evaluation SDK

本地 LLM 作为评判者

认证

Azure 服务主体 / 密钥

无(仅限本地)

成本

按 Token 付费

免费

Install Server
F
license - not found
B
quality
D
maintenance

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.

Related MCP Servers

  • 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.
  • 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
  • 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

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

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

  • 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