How to Use the Baidu Qianfan MCP in LangChain

Connect Baidu Qianfan models directly into your LangChain reasoning pipelines to build custom multi-step agents.

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 LangChain

Create your Vinkius account to connect Baidu Qianfan to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build ReAct Agents with Baidu Qianfan

LangChain turns your basic scripts into autonomous agents. Give your agent the `chat_completions` tool, and it decides when to query Baidu Qianfan based on the intermediate steps of your chain. You define the prompt, and the agent figures out the execution path. Tracing matters when you string multiple LLM calls together. LangSmith captures exactly what goes into the `get_embeddings` tool and tracks the token usage across your entire MCP Server setup. You see the exact latency of every Baidu API hit.

Chain Image Generation Tasks

Visual outputs often require context from other systems. Your LangChain pipeline can pull text from a database, summarize it, and pass that exact string into the `text_to_image` tool. The output URL then feeds into the next step of your chain. You control the flow. If the image generation fails, your setup catches the error and retries the MCP tool automatically. No manual intervention required.

Automate Checks via MCP Server

Stop manually checking your Baidu Qianfan dashboards. You can build a cron-triggered LangChain script that calls `list_train_jobs` every morning. The agent reads the status, formats a report, and dumps it into your Slack channel. Combine this with `list_datasets` to verify your training data actually uploaded before starting a fine-tuning run. Your agent verifies the dataset ID exists and proceeds only when the data is ready.

Setup guide

Set up Baidu Qianfan MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Baidu Qianfan tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "baidu-qianfan-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Baidu Qianfan transactions"
    })
    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 LangChain

Install the langchain-mcp-adapters package. Initialize MultiServerMCPClient with your Vinkius endpoint, call client.get_tools(), and pass them into your agent constructor.

Yes. LangSmith automatically traces every call made through this integration. You get full visibility into latency and token consumption for each request.

The MCP standard abstracts the Baidu API entirely. Your ReAct agent treats Baidu Qianfan just like any other tool in your chain, allowing you to swap models without rewriting integration code.

LangChain agents are stateless by default. You need to use client.session() to maintain conversational memory across multiple tool calls.

This integration only reads metadata. When your LangChain script calls dataset tools, it sees IDs and file names, never the actual dataset contents. Vinkius runs this connection in an isolated sandbox that forgets everything after execution.

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