How to Use the Anyscale MCP in CrewAI

Q: How do I restrict which CrewAI agents can access Anyscale tools?

You use MCPServerHTTP from crewai.mcp and apply a toolfilter. This restricts tools like chatcompletion to your writer agent, keeping your admin tools hidden from general agents.

Q: How do I connect my CrewAI team to the Anyscale MCP Server?

Add your Vinkius server URL to the mcps array when defining your agents. The framework handles the connection handshake and exposes the tools to the crew automatically.

Coordinate specialized CrewAI agent teams to monitor and query Anyscale models autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anyscale MCP to CrewAI

Create your Vinkius account to connect Anyscale 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 Anyscale with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Anyscale Cluster Jobs with Multi-Agent Teams

The `list_jobs` tool gives your operations crew a clear view of running training batches. A monitor agent queries the job list, while an analyst agent evaluates performance metrics. You pass the Vinkius endpoint URL directly in the agent's `mcps` list. This MCP integration lets the crew coordinate sequential tasks, like pausing downstream tasks if a job fails.

Let CrewAI Agents Select the Best Active Anyscale Model

The `list_models` tool allows your research agent to see which open-source LLMs are available on your endpoints. The agent checks this list before assigning generation tasks to writer agents. By filtering tools with `MCPServerHTTP`, you limit model discovery to specific agents. This prevents junior agents from querying expensive models while keeping operations automated.

Monitor Anyscale Deployments via CrewAI MCP Server Tools

The `list_services` tool enables your maintenance agent to check active endpoints. If `get_service` returns an unhealthy state, the agent immediately escalates to your engineering channel. This setup runs completely headless in your CI/CD pipeline. Your crew works in parallel to verify system health without requiring manual terminal commands.

Setup guide

Set up Anyscale 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 Anyscale tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. This restricts tools like `chat_completion` to your writer agent, keeping your admin tools hidden from general agents.

Yes, CrewAI agents run tasks in parallel. They share the same MCP connection to trigger `chat_completion` calls without hitting connection limits on your local machine.

Add your Vinkius server URL to the `mcps` array when defining your agents. The framework handles the connection handshake and exposes the tools to the crew automatically.

This integration supports stdio, SSE, and Streamable HTTP transports. For cloud-hosted multi-agent setups, we recommend using Streamable HTTP for reliable network routing.

Yes, all prompt text and model metadata are sent over TLS directly to your Vinkius sandbox. The isolated environment destroys all session data as soon as your agent crew completes its run.

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