How to Use the Metaplane MCP in CrewAI

Q: Can CrewAI use Metaplane to fix schema errors?

Your crew can identify the drift using listconnectionschemas. Then, you can define an agent task to update your downstream logic.

Q: How do I trigger a check in CrewAI?

Call triggermonitorrun within an agent tool definition. The agent will execute this whenever it deems a check necessary.

Deploy a specialized monitoring crew using the Metaplane MCP server to manage your data quality.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metaplane MCP to CrewAI

Create your Vinkius account to connect Metaplane 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 Metaplane with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor and act with CrewAI

Assign a dedicated agent to call `list_monitors` for constant health checks. Your crew will know exactly when a pipeline stops performing. When an issue appears, have your moderator agent call `get_incident` to prioritize the response. This keeps your team focused on critical failures.

Automated data quality checks

Your research agent can use `list_data_connections` to discover new sources. It keeps your crew updated on the entire data stack. Use `list_connection_schemas` to verify table definitions. This allows your agents to catch schema drift before it ruins your reports.

Historical analysis for your crew

Let your analytical agent inspect `get_monitor_runs` data. It identifies trends that signal impending failures. Your crew can then use `list_configured_alerts` to see who needs to be notified. It ensures the right people get the message immediately.

Setup guide

Set up Metaplane 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 Metaplane tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the server URL to your agent configuration. Your crew can then call tools like `list_incidents` as part of their tasks.

Your crew can identify the drift using `list_connection_schemas`. Then, you can define an agent task to update your downstream logic.

The server requires a single endpoint token. It keeps your Metaplane account isolated while your agents perform their specific duties.

Call `trigger_monitor_run` within an agent tool definition. The agent will execute this whenever it deems a check necessary.

It tracks incident logs, monitor run history, and connection metadata. This ensures your agents only see what they need to manage data health.

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

Mastra AI sdk-typescript

Start using the Metaplane MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started