How to Use the Baidu Qianfan MCP in Claude Code

Q: How do I add the Baidu Qianfan server to Claude Code?

Run claude mcp add --transport http baidu-qianfan-mcp -- in your terminal. Use claude mcp list to confirm it's connected. Your configuration is saved in the /.claude.json file.

Q: Can I use Claude Code to run Baidu Qianfan chat completions in a script?

Yes, that's exactly what it's built for. Call the chatcompletions tool from your shell script and pass it a model and prompt. You can then pipe the standard output to a file or another process.

Q: How do I list my Baidu Qianfan models from the command line with Claude Code?

Use the command claude mcp call baidu-qianfan-mcp listmodels. This executes the tool on the server and prints the JSON list of your available models directly to standard output.

Q: Is it possible to generate images without a GUI?

Yes. The texttoimage tool works headlessly. You call it from a script and handle the output, which will likely be a URL or base64-encoded data that you can then save to a file.

Pipe Baidu Qianfan's AI models into your shell scripts and CI/CD pipelines with Claude Code. Generate text, images, and embeddings from the command line.

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 Claude Code

Create your Vinkius account to connect Baidu Qianfan to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Baidu Qianfan in Your CI/CD Pipeline

This MCP Server lets you call Baidu Qianfan models from any shell environment. Use `chat_completions` in a GitHub Action to auto-generate release notes from your commit logs. The output is just stdout, so you can pipe it to a file or another command. You can also build a pre-deployment check. Have a script use `list_models` to confirm the right model version is active before deploying an application that depends on it. If it's not, the script can fail the build.

Scriptable Image and Embedding Generation

Generate images headlessly from the terminal. A cron job can use the `text_to_image` tool to create a 'chart of the day' and save it to a file. It's all done from the command line, no browser required. The same goes for embeddings. You can write a script that watches a directory, and any time a new text file appears, it calls `get_embeddings` and stores the resulting vector in a database. This is perfect for building automated data processing pipelines.

Manage Models from the Terminal

Stop logging into web UIs to check on things. With Claude Code and this MCP server, you can manage your Baidu Qianfan resources directly. Run `claude mcp call baidu-qianfan-mcp list_train_jobs` to check on fine-tuning progress from your terminal. This makes it easy to query your AI resources as part of a larger script. You can combine it with tools like `jq` to parse the JSON output and script actions based on the results, like sending an alert when a training job completes.

Setup guide

Set up Baidu Qianfan MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see baidu-qianfan-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Baidu Qianfan transactions." It will automatically discover and invoke the available Baidu Qianfan tools.

Terminal

claude mcp add --transport http baidu-qianfan-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Baidu Qianfan MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "baidu-qianfan-mcp": {
      "type": "url",
      "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 Claude Code

Run `claude mcp add --transport http baidu-qianfan-mcp -- ` in your terminal. Use `claude mcp list` to confirm it's connected. Your configuration is saved in the `~/.claude.json` file.

Yes, that's exactly what it's built for. Call the `chat_completions` tool from your shell script and pass it a model and prompt. You can then pipe the standard output to a file or another process.

Use the command `claude mcp call baidu-qianfan-mcp list_models`. This executes the tool on the server and prints the JSON list of your available models directly to standard output.

Yes. The `text_to_image` tool works headlessly. You call it from a script and handle the output, which will likely be a URL or base64-encoded data that you can then save to a file.

The server processes the text prompts and other inputs you provide to tools like `chat_completions`, `text_to_image`, and `get_embeddings`. Each command you run executes in a zero-trust, ephemeral instance on Vinkius. Nothing is stored after the command finishes.

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