SenseCore PlatformをChatGPTとClaudeに接続

• 01 / 03SenseNovaモデルを比較する方法
• 02 / 03スレッドの管理方法
• 03 / 03GPUの稼働状況を監視する

最速日

709ms

最遅日

4419ms

14日間の傾向

遅延傾向+382%

SenseCore Platform Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_WGerX5EoMF3cLaPImYP34A8UFoRYYgmvQyPkRFRu/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — SenseCore Platform capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "sensecore-platform-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_WGerX5EoMF3cLaPImYP34A8UFoRYYgmvQyPkRFRu/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ SenseCore PlatformをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  エンタープライズAI開発者

  SenseTimeの産業用モデルをカスタムアプリケーションへ自動的に統合するエンジニア。

• 02

  インフラストラクチャエンジニア

  GPUクラスターの利用状況やモデルサービスの稼働状態をプログラムで監視する担当者。

• 03

  MLOpsエンジニア

  SenseCoreプラットフォーム上で大規模な推論タスクをオーケストレーションし、追跡する専門家。

• 01

  How do I connect this MCP to my AI client?

  You subscribe to the MCP on Vinkius and then connect your preferred client like Claude, Cursor, or Windsurf. Vinkius handles the hosting and credential management for you.

• 02

  What credentials do I need?

  You will need your API Key and Secret Key from the SenseCore Console, along with your Organization ID and Project ID.

• 03

  Can I monitor GPU usage?

  Yes, the MCP allows you to monitor compute node availability and track quota consumption across your projects.

• 04

  Which models are supported?

  The MCP provides access to the SenseNova model family, including SenseChat, SenseVision, and SenseAudio.

• 05

  Is this for managing individual chats or large tasks?

  It handles both. You can manage individual conversation threads or track the status of large-scale, long-running inference and training tasks.

• 06

  Can I automatically list all available models in my SenseCore project?

  Yes! Use the list_models capability. Your agent will retrieve a complete list of all SenseTime foundation models and specialized variants currently active in your account.

• 07

  How do I check the health status of my deployed model services?

  Use the get_service_health capability with the specific Service ID. The agent will return real-time metrics on availability, throughput, and average latency.

• 08

  Can I monitor GPU resource utilization via the AI agent?

  Yes! The get_resource_usage capability retrieves granular metrics on compute node utilization and remaining quota for your specific project environment.

• 

  CrewAI Platform AIコネクタ

  Orchestrate multi-agent workflows via CrewAI — list crews and agents, kickoff autonomous runs, and monitor tas

  表示
• 

  Kubernetes Architecture Prover AIコネクタ

  An AI generated Kubernetes manifests for a payment service. No resource requests or limits. No PodSecurityStan

  表示
• 

  LiteLLM (LLM Proxy & Spend Tracking) AIコネクタ

  Manage your LLM gateway via LiteLLM — generate API keys, track spending, and orchestrate model fallback paths.

  表示
• 

  LangSmith (LLM Observability & Hub) AIコネクタ

  Monitor LLM apps via LangSmith — track traces, audit prompt templates, and manage evaluation datasets.

  表示

おすすめ

• 

  Langfuse (LLM Tracing & Evals) AIコネクタ

  Monitor LLM apps via Langfuse — track traces, manage prompt templates, and audit evaluation scores.

  表示
• 

  Akash Network (Decentralized GPU & Cloud API) AIコネクタ

  Deploy and manage decentralized GPU and cloud resources on Akash Network—create deployments, manage leases, an

  表示
• 

  Vast.ai (GPU Rental Cloud API) AIコネクタ

  Rent high-performance GPUs for AI and deep learning. Search marketplace offers, deploy Docker containers, and

  表示
• 

  Shunwang Tech AIコネクタ

  Leading edge computing and PC Bang management platform — monitor clusters, schedule tasks, and manage GPU reso

  表示