How to Use the Baseten MCP in CrewAI

Q: How do I pass Baseten tools to a CrewAI agent?

Pass the Baseten MCP Server URL directly into the mcps list when initializing your CrewAI agent. The framework automatically registers tools like predict and listmodels.

Q: Can CrewAI agents coordinate to choose a Baseten model?

Yes, a manager agent can call listmodels to find available options. It then instructs a worker agent to use getmodel and run predictions on the chosen deployment.

Q: How does CrewAI handle errors during a Baseten prediction?

If the predict tool returns an error, the CrewAI agent reads the traceback. The agent then rewrites the input tensor dictionary to match the model's expected schema and retries the call.

Q: Can I limit which Baseten tools my CrewAI agents can use?

Yes, you can use the MCPServerHTTP class from crewai.mcp along with a toolfilter to only expose read tools like listmodels while blocking prediction tools.

Delegate serverless model routing and deployment checks to autonomous agent teams using CrewAI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to CrewAI

Create your Vinkius account to connect Baseten 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 Baseten with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let CrewAI agents run serverless predictions

The `predict` tool lets your agents send input tensors directly to Baseten models for instant serverless inference. It handles formatting the payload to match the model's expected shape. In a CrewAI setup, a researcher agent gathers raw text, while a separate analyst agent uses this tool to run sentiment predictions. The crew passes the results between themselves to complete complex analytical pipelines.

Let agents search models using this MCP Server

The `list_models` tool retrieves all active machine learning models managed in your Baseten workspace. It returns their IDs, configurations, and current statuses. A CrewAI coordinator agent calls this tool to discover which models are available. It then matches the task requirements to the best model before handing the execution over to a specialized sub-agent.

Validate active deployments across your crew

The `get_deployment` tool fetches the exact runtime details of a specific Baseten model deployment. It tells your agent whether the endpoint is active, scaling, or idle. Before running a massive batch prediction, a monitor agent in your crew runs this check. If the deployment is cold, the agent waits or triggers a warm-up call to prevent the main crew from stalling.

Setup guide

Set up Baseten 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 Baseten tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Baseten 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="Baseten Analyst",
        goal="Access and analyze Baseten data via MCP.",
        backstory="Expert analyst with direct Baseten access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Baseten 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 Baseten. 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 Baseten 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 Baseten MCP in CrewAI

Pass the Baseten MCP Server URL directly into the `mcps` list when initializing your CrewAI agent. The framework automatically registers tools like `predict` and `list_models`.

Yes, a manager agent can call `list_models` to find available options. It then instructs a worker agent to use `get_model` and run predictions on the chosen deployment.

If the `predict` tool returns an error, the CrewAI agent reads the traceback. The agent then rewrites the input tensor dictionary to match the model's expected schema and retries the call.

Yes, you can use the `MCPServerHTTP` class from `crewai.mcp` along with a `tool_filter` to only expose read tools like `list_models` while blocking prediction tools.

All communications between CrewAI and Baseten run through secure, authenticated HTTPS endpoints. The Vinkius MCP host uses ephemeral V8 sandboxes that do not store your tensor inputs, model configurations, or secret names.

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