How to Use the Baidu Qianfan MCP in AutoGen

Q: How do I load Baidu Qianfan tools into AutoGen?

Install autogen-extmcp. Use mcpservertools with your Vinkius HTTP endpoint, then pass the resulting list directly into your AssistantAgent constructor.

Give your AutoGen agents the ability to debate and execute Baidu Qianfan tasks through a unified MCP interface.

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 AutoGen

Create your Vinkius account to connect Baidu Qianfan to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Baidu Qianfan Debates

AutoGen agents negotiate before acting. You can build a system where a researcher agent proposes a prompt, and a critic agent refines it. Once they reach consensus, a designated executor agent calls the `chat_completions` tool to get the final response from Baidu. This workflow applies to visual tasks too. A creative agent might draft an image concept while a brand agent checks it against guidelines. Only after they agree does the system trigger the `text_to_image` tool via your MCP Server.

Collaborative Training Management

Managing model fine-tuning requires oversight. Assign one AutoGen agent to monitor your Baidu environment using `list_train_jobs`. If a job fails, this agent alerts a debugging agent to investigate the logs. Pre-flight checks happen automatically. Before starting a new run, a data agent verifies prerequisites by calling `list_datasets`. The agents coordinate to ensure everything is ready, preventing wasted API credits on bad training runs.

Autonomous MCP Server Pipelines

Specialized workers handle specific tasks. You can set up an AutoGen agent dedicated entirely to text processing. This agent takes raw text from other members of the chat, formats it, and executes the `get_embeddings` tool. The resulting vectors feed right back into the multi-agent conversation. Other agents then use that vector data to inform their own decisions, all coordinated through standard MCP tool calls.

Setup guide

Set up Baidu Qianfan MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Baidu Qianfan tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Baidu Qianfan_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Baidu Qianfan data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Baidu Qianfan_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Baidu Qianfan data")
    print(result.messages[-1].content)

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 AutoGen

Install autogen-ext[mcp]. Use mcp_server_tools with your Vinkius HTTP endpoint, then pass the resulting list directly into your AssistantAgent constructor.

Yes. You can assign the tool list to specific agents in your roster. One agent can handle image generation while another manages chat completions.

The McpToolAdapter handles this automatically. AutoGen translates its internal tool requests into the exact JSON schema required by the MCP standard.

Yes. The Streamable HTTP transport connects your local multi-agent setup to the remote Vinkius environment without exposing API keys locally.

The multi-agent chat history remains local to your AutoGen environment. Only the specific text strings passed explicitly to the tools are sent to the ephemeral Vinkius sandbox for processing.

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