How to Use the Metaplane MCP in AutoGen

Q: How do I register Metaplane tools with AutoGen agents?

Install autogen-extmcp and use the MCP server tools configuration with your server's connection parameters. Pass the resulting tool list directly to your AutoGen AssistantAgent constructor.

Q: Can AutoGen agents negotiate how to resolve a Metaplane incident?

Yes, one agent can fetch incident details using getincident while another checks the run history via getmonitorruns. They then debate the best resolution path before invoking any external actions.

Q: How do AutoGen agents access Metaplane connection details?

Agents call listdataconnections to discover active warehouses and databases. They use this information to dynamically target their schema verification tasks using listconnectionschemas.

Build AutoGen agent debates to resolve Metaplane data quality incidents automatically.

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 AutoGen

Create your Vinkius account to connect Metaplane to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Metaplane triage debates in AutoGen

Your AutoGen triage agent calls `list_incidents` to identify active data quality issues and shares the details with a specialist debugging agent. The debugging agent then calls `get_incident` to analyze the root cause, debating the priority of the fix with your performance agent. This multi-agent conversation ensures that critical schema changes aren't ignored. The agents negotiate whether to pause downstream jobs or trigger immediate alerts based on the severity metrics returned by the server.

Automate monitor verification via this MCP Server

An AutoGen supervisor agent uses this MCP Server to execute `trigger_monitor_run` after a database migration. A validation agent then monitors `get_monitor_runs` to verify the run succeeded before giving the green light to proceed. By separating the trigger and verification roles between distinct AutoGen agents, you eliminate single-point-of-failure scripts. The agents cross-reference the results against your active `list_monitors` configuration to guarantee compliance.

Map connection schemas using AutoGen agent teams

Your database agent queries `list_data_connections` and passes the active connections to a schema agent. The schema agent then calls `list_connection_schemas` to verify that all required tables exist and match the expected structures. If a discrepancy is found, the agents collaborate to draft a fix, querying `list_configured_alerts` to find the correct team channel for escalation. This cooperative workflow keeps your data infrastructure aligned without manual developer oversight.

Setup guide

Set up Metaplane MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Metaplane tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Metaplane_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Metaplane data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Metaplane_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Metaplane data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` and use the MCP server tools configuration with your server's connection parameters. Pass the resulting tool list directly to your AutoGen `AssistantAgent` constructor.

Yes, one agent can fetch incident details using `get_incident` while another checks the run history via `get_monitor_runs`. They then debate the best resolution path before invoking any external actions.

Agents call `list_data_connections` to discover active warehouses and databases. They use this information to dynamically target their schema verification tasks using `list_connection_schemas`.

AutoGen supports both stdio and HTTP transports for this MCP integration. This allows you to run the Metaplane integration locally during development or host it as a microservice in production.

No, the server only returns high-level metadata such as incident states from `list_incidents` and monitor histories from `get_monitor_runs`. Your database credentials and connection strings are never exposed to the AutoGen agents.

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