How to Use the Cerebras Inference MCP in CrewAI

Q: Can I assign different Cerebras Inference tools to different agents in my CrewAI crew?

Yes. For more control, use the MCPServerHTTP class from crewai.mcp and provide a toolfilter. This lets you create multiple server instances in your code, each exposing a different subset of tools to specific agents.

Q: How would a crew collaborate on a Cerebras Inference batch job using CrewAI?

You'd create a SequentialTask list. Task 1, for a 'Submitter' agent, uses createbatch. Task 2, for a 'Watcher' agent, polls getbatch until it's done. Task 3, for a 'Summarizer' agent, uses getfilecontent to report the results.

Deploy autonomous agent crews on Cerebras with CrewAI. Let one agent manage batch jobs while another analyzes the output.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cerebras Inference MCP to CrewAI

Create your Vinkius account to connect Cerebras Inference 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 Cerebras Inference with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

The Inference Operations Crew

Assign roles to your CrewAI agents for a complete workflow. A 'Scheduler' agent can use `create_batch` to start jobs, while a 'Monitor' agent periodically calls `get_batch` to check the status. Once a job is complete, the Monitor agent delegates to an 'Analyst' agent. The Analyst uses `get_file_content` to download the results and `create_chat_completion` to summarize the findings or decide on the next action.

Model Management Specialists

Dedicate an agent to be your 'Model Curator.' This agent's only job is to use `list_models` and `get_model` to maintain an up-to-date picture of the available Cerebras models. It passes this information into the crew's shared memory. Other agents, like a 'Generator' agent, can then access this shared context before calling `create_completion`. This makes the crew adaptive—it won't fail if a model is deprecated or a new one comes online.

Your CrewAI MCP Server for Cerebras

Give your crew the tools for self-sufficiency. A 'Janitor' agent can be tasked with cleanup, using `list_files` and `list_batches` to find old artifacts and then calling `delete_file` or `cancel_batch` to free up resources. This MCP server integration is flexible. You can expose all 15 tools to a 'Manager' agent or use `tool_filter` to give specialized agents only the tools they need, like providing `get_metrics` only to a 'System Monitor' agent.

Setup guide

Set up Cerebras Inference 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 Cerebras Inference tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The simplest way is to pass your Vinkius MCP URL directly into the `mcps` list when you define an Agent. CrewAI will automatically discover and equip the agent with all the available tools.

Yes. For more control, use the `MCPServerHTTP` class from `crewai.mcp` and provide a `tool_filter`. This lets you create multiple server instances in your code, each exposing a different subset of tools to specific agents.

You'd create a `SequentialTask` list. Task 1, for a 'Submitter' agent, uses `create_batch`. Task 2, for a 'Watcher' agent, polls `get_batch` until it's done. Task 3, for a 'Summarizer' agent, uses `get_file_content` to report the results.

It works with both. You could have a manager agent delegate `create_completion` tasks to subordinate agents in a hierarchy, or have agents hand off the results of a `get_batch` call to the next agent in a sequence.

Vinkius processes all MCP server requests in isolated, zero-trust sandboxes. Your data, including any JSONL files uploaded for batch inference, is handled ephemerally. You can, and should, have an agent use the `delete_file` tool to explicitly remove your data after 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