Baidu QianfanをChatGPT、Claude、Geminiに接続

• 01 / 03コンテンツ制作の自動化について
• 02 / 03RAG知識ベースの構築方法
• 03 / 03LLMの比較方法

最速日

659ms

最遅日

1265ms

14日間の傾向

遅延傾向+8%

Baidu Qianfan 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_nSPMSdk1YEMCwy7aSAehImUREP7520Z8lSHvuSUL/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 — Baidu Qianfan capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "baidu-qianfan-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_nSPMSdk1YEMCwy7aSAehImUREP7520Z8lSHvuSUL/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？ Baidu Qianfan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

  AI開発者

  複数のErnieモデルバージョンを比較・検証し、最適なAIロジックを構築したい開発者。

• 02

  システムインテグレーター

  企業アプリケーションと百度の高性能な中国語LLMを橋渡しし、大規模なシステム統合を実現したい技術者。

• 03

  ナレッジマネージャー

  Qianfanの埋め込み機能とチャットサービスを活用し、堅牢なRAGパイプラインを構築したい管理者。

• 01

  Is this MCP only for Chinese language models?

  No. While it connects to Baidu Qianfan, which is an enterprise-grade Chinese LLM platform, it provides capabilities for managing multiple model interactions and services.

• 02

  What is the difference between chat completions and embeddings?

  Chat completions is for conversational dialogue, where you send a message and get a response. Embeddings, generated by the get_embeddings capability, are numerical vectors used to represent text for search and indexing.

• 03

  Do I need to worry about API keys?

  Yes. You must create an application in the Baidu Qianfan Console to obtain your API Key and Secret Key, which you then provide to the MCP.

• 04

  Can I use this for image generation?

  Yes. The text_to_image capability lets you generate visual content by simply providing a descriptive text prompt.

• 05

  What if I want to check my usage?

  You can programmatically track token consumption and manage model service status using the available capabilities.

• 06

  Which version of Ernie Bot should I use for chat?

  For high performance and reasoning, use ernie-4.0-8k. For faster response times and cost efficiency, ernie-speed-128k or ernie-lite-8k are excellent choices.

• 07

  Can I automatically generate embeddings for RAG?

  Yes! Use the get_embeddings capability with your text input. The agent will retrieve the vector representations from Baidu's embedding models, ready for indexing in your vector database.

• 08

  How do I use prompt templates from the console?

  Use the list_prompt_templates capability to find your configured templates. You can then retrieve specific details using get_prompt_template to maintain consistency across your AI workflows.

• 

  Cloud BOT AIコネクタ

  Run automated browser tasks in the cloud with scriptless bots that extract data, fill forms, and navigate webs

  表示
• 

  Mistral AI (Frontier LLMs & Embeddings) AIコネクタ

  Manage AI inference via Mistral — execute chat completions, generate RAG embeddings, and audit frontier models

  表示
• 

  Datadog AI (LLM Observability) AIコネクタ

  Monitor LLM performance via Datadog — track token usage, audit prompts, and monitor AI model metrics directly

  表示
• 

  Helicone (LLM Observability) AIコネクタ

  Monitor LLM usage via Helicone — track requests, analyze costs, measure latency, and manage prompts.

  表示

おすすめ

• 

  Prompt Template Reuse Analyzer AIコネクタ

  A diagnostic engine to evaluate prompt library efficiency and identify consolidation opportunities.

  表示
• 

  Humanloop (LLM Prompt Management API) AIコネクタ

  Manage, version, and deploy LLM prompts directly from your AI agent using the Humanloop API.

  表示
• 

  Prompt Template Variable Injector Checker AIコネクタ

  Validates prompt templates for syntax, undeclared variables, and injection risks.

  表示
• 

  Prompt Template Consistency Checker AIコネクタ

  Validates consistency between prompt templates and context dictionaries.

  表示