How to Use the Baidu Qianfan MCP in Mastra AI

Q: How do I register the Baidu Qianfan tools inside a Mastra AI agent?

Initialize the MCP client in your TypeScript code, call listTools(), and spread those tools directly into your agent's tool array. The agent will then autonomously decide when to call Baidu's APIs.

Build resilient TypeScript workflows around Baidu Qianfan models with Mastra AI's automated retries and branching.

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 Mastra AI

Create your Vinkius account to connect Baidu Qianfan to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Qianfan training runs with Mastra AI

Training LLMs is notoriously flaky, but you can build self-healing pipelines by hooking Mastra's workflow engine to the `list_train_jobs` tool. If a Baidu training job fails, Mastra can catch the error, trigger a retry with exponential backoff, or branch to a backup model. This means you don't have to manually monitor your fine-tuning runs. The server lets your Mastra agent check the status of active runs and automatically kick off a new job if the metrics look off.

Build conditional image workflows with Mastra

Sometimes Baidu's `text_to_image` tool might return an error or an unexpected result. Mastra allows you to set up conditional branching to inspect the output before displaying it. If the image generation fails, Mastra's workflow engine can automatically reroute the request to `chat_completions` to rewrite the prompt and try again. This keeps your agent running without crashing your TypeScript backend.

Dynamic dataset syncing via Mastra AI MCP Server

Keep your training data fresh by using Mastra agents to orchestrate files. By calling `list_datasets` and comparing them against your local files, your agent can decide when to upload new data to Baidu's platform. You spread the MCP tools directly into your Mastra agent definition. The agent then autonomously decides when to query `list_models` to see if a newly trained version is ready for deployment.

Setup guide

Set up Baidu Qianfan MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Baidu Qianfan tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "baidu-qianfan-mcp-client",
  servers: {
    "baidu-qianfan-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Baidu Qianfan Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Baidu Qianfan tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Baidu Qianfan transactions"
);
console.log(result.text);

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 Mastra AI

Mastra features a built-in workflow engine with automatic retries. If a `chat_completions` request hits a rate limit on the Baidu Qianfan endpoint, Mastra backs off and retries the call automatically.

Yes. You can configure Mastra's workflow to require human-in-the-loop approval before executing the `list_train_jobs` tool or starting a new fine-tuning run.

Initialize the MCP client in your TypeScript code, call `listTools()`, and spread those tools directly into your agent's tool array. The agent will then autonomously decide when to call Baidu's APIs.

Yes. Mastra automatically detects the transport type exposed by Vinkius. It will establish a secure connection to the hosted MCP Server without requiring complex networking setups.

They go directly to Baidu's API endpoints. Vinkius operates a zero-trust, ephemeral sandbox that only proxies your `chat_completions` payloads, ensuring no prompt text is ever written to disk.

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