How to Use the Metaplane MCP in Pydantic AI

Q: How do I initialize the Metaplane toolset in Pydantic AI?

Use MCPToolset with your Vinkius HTTP endpoint and pass it to your Agent constructor. This registers all 10 MCP tools, including listmonitors, with automatic runtime type validation.

Q: Can I run Metaplane monitors asynchronously in Pydantic AI?

Yes. You can call triggermonitorrun asynchronously and poll getmonitorruns to track progress. The agent handles the async loop while validating each response.

Bring type-safe data observability to Pydantic AI agents to validate warehouse health without silent failures.

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 Pydantic AI

Create your Vinkius account to connect Metaplane to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe schema validation in Pydantic AI

The `list_connection_schemas` tool returns structured metadata that Pydantic AI validates against strict runtime models. If a warehouse schema changes, the agent catches the mismatch instantly instead of passing corrupt data down the line. This MCP Server integration guarantees that every database connection returned by `list_data_connections` conforms to your expected types. Your agent works with clean, predictable data structures every single time.

Strict incident tracking

The `list_incidents` tool fetches active data quality issues and parses them directly into validated Python objects. Your agent uses `get_incident` to extract precise details about the failure, ensuring no missing fields go unnoticed. By enforcing strict validation, your agent avoids hallucinating details about broken pipelines. It processes actual, structured incident data, making automated triage highly reliable.

Validate monitor execution

The `get_monitor_runs` tool retrieves the execution history for your data quality checks, validating every timestamp and status code. Your agent triggers new checks using `trigger_monitor_run` and monitors the state safely. This strict type checking prevents your agent from misinterpreting test results. It inspects the run history, checks specific monitor details with `get_monitor`, and raises explicit errors if a run fails.

Setup guide

Set up Metaplane MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "metaplane-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Metaplane tools.",
)

result = await agent.run("List recent Metaplane transactions")
print(result.output)

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 Pydantic AI

Use `MCPToolset` with your Vinkius HTTP endpoint and pass it to your `Agent` constructor. This registers all 10 MCP tools, including `list_monitors`, with automatic runtime type validation.

The framework raises a validation error immediately, stopping execution before the agent can act on bad data. This prevents silent failures when querying endpoints like `list_incidents`.

Yes. You can call `trigger_monitor_run` asynchronously and poll `get_monitor_runs` to track progress. The agent handles the async loop while validating each response.

No. Vinkius hosts and manages the MCP Server in a secure cloud sandbox. Your Python code only needs the connection URL to start querying your data monitors.

All data transit between Pydantic AI and your warehouse metadata is encrypted. Vinkius isolates your API tokens in ephemeral containers, ensuring your internal pipeline metrics are never exposed outside the MCP session.

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