How to Use the Baidu Qianfan MCP in Cline

Q: What's required to use the chat completions tool?

The chatcompletions tool requires you to specify a model endpoint name. You can get a list of your available models first by telling Cline to use the listmodels tool.

Hook Baidu Qianfan into Cline to generate code, text, and images inside VS Code. Let Cline build entire components using Baidu's models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baidu Qianfan MCP to Cline

Create your Vinkius account to connect Baidu Qianfan to Cline and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Baidu Qianfan with Cline

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Components with AI-Generated Content

Tell Cline to build a React component that displays AI-generated text. It will use the `chat_completions` tool to get content from Baidu Qianfan, write the component code itself, and stage the new file for you. You just give the high-level instruction. This works for images, too. Ask Cline to create a placeholder component with an image. It'll call the `text_to_image` tool and embed the result. End-to-end task execution means you're reviewing a finished diff, not writing boilerplate code.

Automate Model Management in VS Code

Stop switching contexts just to check on your models. With this MCP Server, you can ask Cline to 'list my current Baidu Qianfan training jobs.' It calls `list_train_jobs` and shows you the status right in your editor. The same goes for `list_models` and `list_datasets`. This is great for keeping your workflow inside a single window. You can have Cline check model availability before running a generation script, making sure everything is ready to go without any manual checks.

Connect Cline to Your Baidu Qianfan MCP Server

Connecting Cline to your Baidu models makes it a true workhorse. It can now use `get_embeddings` to vectorize text from an open file, then use that data to inform another action. Cline doesn't just call tools; it chains them together to complete a goal. For example, you could tell Cline to 'analyze the sentiment of user_feedback.txt'. It could read the file, send the content to `get_embeddings` via this server, and then use the vectors to classify the feedback. All from one prompt.

Setup guide

Set up Baidu Qianfan MCP in Cline

Prerequisites

VS Code with Cline extension installed
Active Vinkius subscription with a valid endpoint token

1

Open Cline MCP settings

Click the Cline icon in the VS Code sidebar to open the Cline panel. Then click the MCP Servers icon (server stack) at the top-right corner of the panel.
2

Add a remote server

Click "Remote Servers" at the top, then click "Add Remote MCP". In the Name field, type baidu-qianfan-mcp. In the URL field, paste your Vinkius endpoint: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp. Get your token from cloud.vinkius.com.
3

Enable the server

After saving, the server appears in the Cline MCP panel. Toggle the switch to enable it. The status indicator turns green when the connection is live.
4

Start using tools

Return to the Cline chat and ask: "Check my latest Baidu Qianfan refund status." Cline will discover the available tools and request your approval before invoking each one — giving you full control over every action.

Cline MCP Settings

{
  "mcpServers": {
    "baidu-qianfan-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Baidu Qianfan. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Baidu Qianfan now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Baidu Qianfan MCP in Cline

Open the Cline sidebar in VS Code and go to the MCP Servers icon. You can install it from the Marketplace tab with one click. You can also add it by URL in the Remote Servers tab.

Definitely. Tell Cline something like, 'generate embeddings for the text in this file.' It will read the active file's contents and pass them to the `get_embeddings` tool from the Baidu Qianfan server.

It does. You can ask Cline to 'show me my datasets on Baidu Qianfan.' It uses the `list_datasets` tool to fetch and display that information for you, right inside the editor.

The `chat_completions` tool requires you to specify a model endpoint name. You can get a list of your available models first by telling Cline to use the `list_models` tool.

The server only handles the text prompts and content you send for generation or embedding. Vinkius processes these requests in isolated V8 sandboxes that are destroyed after execution. Your connection is secured by a single endpoint token, never raw credentials.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript