How to Use the Metorial MCP in CrewAI

Q: How do I add Metorial MCP Server tools to a CrewAI agent?

Pass your serverless endpoint URL directly to the mcps array when defining the agent. For advanced setups, use MCPServerHTTP to filter specific tools for different roles.

Q: Can a CrewAI supervisor agent deploy Metorial servers dynamically?

Yes. Give the supervisor agent access to metorialdeployserver so it can spin up new worker nodes as the queue of tasks grows.

Q: How does Metorial handle concurrent MCP tool calls from multiple CrewAI agents?

The serverless infrastructure uses metorialinvokeservertool to execute calls in parallel across isolated container instances, preventing execution bottlenecks.

Coordinate multi-agent teams with serverless Metorial scaling and CrewAI memory.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metorial MCP to CrewAI

Create your Vinkius account to connect Metorial 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 Metorial with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dedicated worker environments for agent crews

`metorial_deploy_server` provisions isolated environments for specific CrewAI agents. A researcher agent can run in one container while an analyst agent operates in another, preventing dependency conflicts. If an agent finishes its assignment, `metorial_delete_server` immediately deallocates the container. This dynamic scaling keeps compute costs low when running large, multi-agent pipelines.

Trace logging for collaborative MCP Server tasks

`metorial_list_traces` aggregates the execution logs of all agents working in your crew. You can see how Agent A's output served as the input for Agent B's tool invocation. When debugging a failed handoff, `metorial_get_trace_details` provides the exact payload boundaries. This eliminates the guesswork when tracking down state issues in complex agent teams.

Multi-agent load balancing and metrics

`metorial_get_usage_metrics` monitors the resource consumption of each active agent container. Your manager agent can inspect these metrics to distribute tasks to the most cost-efficient worker nodes. By using `metorial_list_servers`, the supervisor agent keeps an active inventory of available workspace nodes. It routes tasks to warm servers to avoid cold-start delays.

Setup guide

Set up Metorial 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 Metorial tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your serverless endpoint URL directly to the `mcps` array when defining the agent. For advanced setups, use `MCPServerHTTP` to filter specific tools for different roles.

Yes. Give the supervisor agent access to `metorial_deploy_server` so it can spin up new worker nodes as the queue of tasks grows.

The serverless infrastructure uses `metorial_invoke_server_tool` to execute calls in parallel across isolated container instances, preventing execution bottlenecks.

CrewAI maintains agent memory locally or in your vector database. Resetting a server via `metorial_delete_server` only clears the execution container, not the crew's memory.

All agent interaction boundaries and transaction histories are written to an encrypted, ephemeral datastore. These traces are accessible only via your secure workspace token, preventing data exposure.

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