How to Use the Baidu Qianfan MCP in CrewAI

Q: Can I limit which Baidu Qianfan tools a CrewAI agent can use?

Yes. You can use the MCPServerHTTP class from crewai.mcp with a toolfilter to expose only specific tools, like getembeddings, to certain agents while keeping training tools restricted.

Q: Are my Baidu Qianfan vector embeddings secure?

Yes. When your agents call getembeddings through the MCP Server, the raw text is sent directly to Baidu's endpoint via Vinkius's secure, isolated network. No embedding vectors or source texts are stored.

Deploy specialized agent teams that collaborate to train models and generate assets using Baidu Qianfan and CrewAI.

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 CrewAI

Create your Vinkius account to connect Baidu Qianfan to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Qianfan fine-tuning with CrewAI

Set up a CrewAI team where one agent monitors training runs while another prepares data. By giving your crew access to `list_train_jobs` and `list_datasets`, they can collaborate to track training progress without human oversight. For example, a researcher agent checks the dataset list, while a manager agent decides if it's time to trigger a fine-tuning run. This multi-agent structure ensures your Baidu models are always trained on the latest inputs.

Multi-agent design loops using this MCP Server

Build a crew where a copywriter agent drafts prompts and a designer agent turns them into images. The copywriter calls `chat_completions` to refine the prompt, then passes it to the designer who executes `text_to_image`. This collaborative loop happens autonomously. The agents use shared memory to critique the output, ensuring the final asset generated via the Baidu Qianfan server meets your quality standards before saving.

Autonomous model routing in CrewAI

Let your crew dynamically select the best model for a task. An analyst agent can call `list_models` to check available endpoints, while a coder agent uses `get_embeddings` to find the most relevant context for the prompt. Instead of hardcoding model names, your crew evaluates the active services on Baidu's platform in real-time. This keeps your autonomous operations highly adaptable to API changes.

Setup guide

Set up Baidu Qianfan MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Baidu Qianfan tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Baidu Qianfan Analyst",
    goal="Access and analyze Baidu Qianfan data via MCP.",
    backstory="Expert analyst with direct Baidu Qianfan access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Baidu Qianfan transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Baidu Qianfan Analyst",
        goal="Access and analyze Baidu Qianfan data via MCP.",
        backstory="Expert analyst with direct Baidu Qianfan access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Baidu Qianfan transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the Vinkius MCP URL directly to your CrewAI agents using the `mcps` parameter. Each agent in the crew can then access tools like `chat_completions` or `text_to_image` depending on their assigned role.

Yes. You can use the `MCPServerHTTP` class from `crewai.mcp` with a `tool_filter` to expose only specific tools, like `get_embeddings`, to certain agents while keeping training tools restricted.

CrewAI manages agent execution sequentially or hierarchically. If multiple agents call `chat_completions` at the same time, the underlying MCP client queues the requests to prevent rate-limiting on Baidu's side.

No. The hosted server handles all communication with Baidu's APIs. Your Python environment only needs `crewai` and its standard tool packages installed.

Yes. When your agents call `get_embeddings` through the MCP Server, the raw text is sent directly to Baidu's endpoint via Vinkius's secure, isolated network. No embedding vectors or source texts are stored.

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