Rhoai MCP Prototype

RHOAI MCP服务器

  ](https://github.com/opendatahub-io/rhoai-mcp)   

MCP（模型上下文协议）服务器，使AI代理能够与Red Hat OpenShift AI（RHOAI）环境进行交互。此服务器通过编程工具复制OpenShift AI仪表板的功能。

特性

• 项目管理：创建、列出和管理数据科学项目
• 工作台操作：创建、启动、停止和删除Jupyter工作台
• 模特服务：使用KServe部署和管理InferenceServices
• 数据连接：管理数据访问的S3凭据
• 管道：配置数据科学管道基础设施
• 存储：创建和管理持久数量声明
• 训练：使用Kubeflow Training Operator对模型进行微调
• MCP提示：多步骤操作的工作流程指南（18个提示）

技术栈

安装

使用紫外线（推荐）

# Clone the repository
git clone https://github.com/admiller/rhoai-mcp-prototype.git
cd rhoai-mcp-prototype

# Install dependencies
uv sync

# Run the server
uv run rhoai-mcp

使用pip

pip install -e .
rhoai-mcp

使用容器（Podman/Docker）

# Build the image
make build

# Run with HTTP transport
make run-http

# Run with STDIO transport (interactive)
make run-stdio

# Run with debug logging
make run-dev

或者直接运行而不使用Make：

# Build
podman build -f Containerfile -t rhoai-mcp:latest .

# Run with HTTP transport
podman run -p 8000:8000 \
  -v ~/.kube/config:/opt/app-root/src/kubeconfig/config:ro \
  -e RHOAI_MCP_AUTH_MODE=kubeconfig \
  -e RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config \
  rhoai-mcp:latest --transport sse

# Run with STDIO transport
podman run -it \
  -v ~/.kube/config:/opt/app-root/src/kubeconfig/config:ro \
  -e RHOAI_MCP_AUTH_MODE=kubeconfig \
  -e RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config \
  rhoai-mcp:latest --transport stdio

可用目标：

Kubernetes部署

对于集群内部署，应用Kubernetes清单：

kubectl apply -f deploy/kubernetes/deployment.yaml

这将创建：

• 命名空间 rhoai-mcp
• RHOAI资源的RBAC服务帐户
• 使用SSE传输运行MCP服务器的部署
• 服务暴露端口8000
• 带TLS终止的路由（仅限OpenShift）

配置

服务器可以通过环境变量进行配置（ RHOAI_MCP_ 前缀）或a .env 文件。

认证

服务器支持三种身份验证模式：

1. 自动（默认）：首先尝试集群身份验证，然后回退到kubeconfig
2. Kubeconfig：使用kubeconfig文件
3. 代币：使用明确的API服务器URL和令牌

# Auto mode (default)
export RHOAI_MCP_AUTH_MODE=auto

# Kubeconfig mode
export RHOAI_MCP_AUTH_MODE=kubeconfig
export RHOAI_MCP_KUBECONFIG_PATH=/path/to/kubeconfig
export RHOAI_MCP_KUBECONFIG_CONTEXT=my-context

# Token mode
export RHOAI_MCP_AUTH_MODE=token
export RHOAI_MCP_API_SERVER=https://api.cluster.example.com:6443
export RHOAI_MCP_API_TOKEN=sha256~xxxxx

运输

# stdio (default) - for Claude Desktop and similar tools
export RHOAI_MCP_TRANSPORT=stdio

# HTTP transports
export RHOAI_MCP_TRANSPORT=sse
export RHOAI_MCP_HOST=127.0.0.1
export RHOAI_MCP_PORT=8000

安全设置

# Enable delete operations (disabled by default)
export RHOAI_MCP_ENABLE_DANGEROUS_OPERATIONS=true

# Read-only mode (disable all write operations)
export RHOAI_MCP_READ_ONLY_MODE=true

安全特性概述

模型注册表

MCP服务器与RHOAI模型注册表集成，以列出和查询已注册的模型。默认情况下，它会自动发现群集中的模型注册表服务。

发现模式

# Auto-discovery (default) - finds Model Registry in the cluster
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=auto

# Manual - use a specific URL
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=manual
export RHOAI_MCP_MODEL_REGISTRY_URL=https://model-registry.example.com

认证

当通过外部路由（集群外）访问模型注册表时，通常需要进行身份验证（OAuth用于OAuth代理路由；还支持显式令牌身份验证）：

# No authentication (default) - for in-cluster access
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=none

# OAuth authentication - uses your oc login token
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=oauth

# Explicit token authentication
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=token
export RHOAI_MCP_MODEL_REGISTRY_TOKEN=sha256~xxxxx

外部路由访问

要通过OpenShift路由从集群外部访问模型注册表，请执行以下操作：

# 1. Log in to OpenShift (this stores the OAuth token in kubeconfig)
oc login --server=https://api.cluster.example.com:6443

# 2. Configure the MCP server to use the external route with OAuth
export RHOAI_MCP_MODEL_REGISTRY_URL=https://model-catalog.apps.cluster.example.com
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=manual
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=oauth

# 3. Optional: Skip TLS verification for self-signed certificates (not recommended)
# export RHOAI_MCP_MODEL_REGISTRY_SKIP_TLS_VERIFY=true

端口转发替代方案

如果没有可用的外部路由，您可以使用端口转发：

# Set up port-forwarding to the Model Registry service
kubectl port-forward -n rhoai-model-registries svc/model-catalog 8080:8443

# Configure the MCP server to use localhost
export RHOAI_MCP_MODEL_REGISTRY_URL=http://localhost:8080
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=manual

所有模型注册表设置

使用Claude代码

添加到您的项目 .mcp.json 文件：

{
  "mcpServers": {
    "rhoai": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/opendatahub-io/rhoai-mcp", "rhoai-mcp"],
      "env": {
        "RHOAI_MCP_KUBECONFIG_PATH": "/home/user/.kube/config"
      }
    }
  }
}

使用Claude Desktop

添加到您的Claude Desktop配置(~/.config/claude/claude_desktop_config.json):

{
  "mcpServers": {
    "rhoai": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/opendatahub-io/rhoai-mcp", "rhoai-mcp"],
      "env": {
        "RHOAI_MCP_KUBECONFIG_PATH": "/home/user/.kube/config"
      }
    }
  }
}

本地开发

对于使用本地克隆的贡献者：

{
  "mcpServers": {
    "rhoai": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/rhoai-mcp", "rhoai-mcp"],
      "env": {
        "RHOAI_MCP_KUBECONFIG_PATH": "/home/user/.kube/config"
      }
    }
  }
}

使用容器镜像（Podman/Docker）

首先，构建容器映像：

make build

然后使用容器配置Claude Desktop：

子程序 ：

{
  "mcpServers": {
    "rhoai": {
      "command": "podman",
      "args": [
        "run", "-i", "--rm",
        "--userns=keep-id",
        "-v", "${HOME}/.kube/config:/opt/app-root/src/kubeconfig/config:ro",
        "-e", "RHOAI_MCP_AUTH_MODE=kubeconfig",
        "-e", "RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config",
        "rhoai-mcp:latest"
      ]
    }
  }
}

Docker：

{
  "mcpServers": {
    "rhoai": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-v", "${HOME}/.kube/config:/opt/app-root/src/kubeconfig/config:ro",
        "-e", "RHOAI_MCP_AUTH_MODE=kubeconfig",
        "-e", "RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config",
        "rhoai-mcp:latest"
      ]
    }
  }
}

注：容器使用 stdio 默认情况下，这是Claude Desktop集成所必需的。

可用工具

项目管理（6个工具）

工作台管理（8个工具）

模型服务（6个工具）

数据连接（4个工具）

管道（3个工具）

存储（3个工具）

MCP资源

服务器还公开只读资源：

MCP提示

该服务器提供18个提示，指导AI代理完成多步工作流程。提示是提供分步说明的模板，并参考每个工作流阶段的适当工具。

培训工作流程（3个提示）

集群探索（4个提示）

故障排除（4个提示）

项目设置（3个提示）

模型部署（4个提示）

交互示例

创建数据科学项目

User: Create a new data science project called "fraud-detection" for my ML experiments
Agent: I'll create that project for you with a descriptive display name.
[Calls create_data_science_project with name="fraud-detection", 
 display_name="Fraud Detection ML", description="Machine learning experiments for fraud detection"]

Result: Project 'fraud-detection' created successfully

部署模型

User: Deploy my trained fraud model from S3 to the fraud-detection project

Agent: I'll deploy your model. First, let me check available serving runtimes.
[Calls list_serving_runtimes with namespace="fraud-detection"]
[Calls deploy_model with name="fraud-model", namespace="fraud-detection",
 runtime="ovms", model_format="onnx", 
 storage_uri="s3://models/fraud-detection/model.onnx"]

Result: Model 'fraud-model' deployment initiated. It may take a few minutes to become ready.

检查项目状态

User: What's the status of my fraud-detection project?

Agent: [Calls get_project_status with namespace="fraud-detection"]

Result:
- Project: fraud-detection (Fraud Detection ML)
- Workbenches: 2 total, 1 running
- Models: 1 deployed, 1 ready
- Pipeline Server: Ready
- Data Connections: 1
- Storage: 3 PVCs

发展

运行测试

# Install dev dependencies
uv sync --extra dev

# Run tests
uv run pytest

# Run with coverage
uv run pytest --cov=rhoai_mcp

代码质量

# Format code
uv run ruff format

# Lint
uv run ruff check

# Type check
uv run mypy src/rhoai_mcp

建筑

┌─────────────────────────────────────────────────────────────────┐
│                MCP Transport Layer (stdio/SSE/HTTP)             │
├─────────────────────────────────────────────────────────────────┤
│  FastMCP Server (server.py)                                     │
│  - Tool registration     - Resource registration                │
│  - Prompt registration   - Lifecycle management                 │
├───────────────────┬─────────────────────┬───────────────────────┤
│  Tools Layer      │  Resources Layer    │  Prompts Layer        │
│  - projects       │  - cluster.py       │  - training (3)       │
│  - notebooks      │  - projects.py      │  - exploration (4)    │
│  - inference      │                     │  - troubleshooting (4)│
│  - connections    │                     │  - project setup (3)  │
│  - storage        │                     │  - deployment (4)     │
│  - pipelines      │                     │                       │
│  - training       │                     │                       │
├───────────────────┴─────────────────────┴───────────────────────┤
│  Clients Layer (clients/) - Business Logic                      │
│  - base.py (K8sClient)   - projects.py    - notebooks.py        │
│  - inference.py          - connections.py - storage.py          │
│  - pipelines.py          - training.py                          │
├─────────────────────────────────────────────────────────────────┤
│  Models Layer (models/) - Pydantic Data Structures              │
│  - common.py (shared)    - Domain-specific models per resource  │
├─────────────────────────────────────────────────────────────────┤
│  Infrastructure Layer                                           │
│  - K8sClient: Kubernetes API abstraction (Core + CRDs)          │
│  - Configuration: Environment-based settings                    │
│  - Plugin Manager: Pluggy-based plugin system                   │
└─────────────────────────────────────────────────────────────────┘

目录结构

请求流

AI Agent Request → MCP Transport → Tool Handler → Domain Client
                                                       ↓
AI Agent Response ← Pydantic Model ← K8s Response ← K8sClient → Kubernetes API

支持的关键CRD

许可证

MIT许可证-请参阅 许可证 了解详情。