How to Use the Metorial MCP in Pydantic AI

Q: Can I check my serverless costs in Pydantic AI?

Call metorialgetusagemetrics to see your current latency and cost data. It integrates into your Pydantic AI workflow to provide real-time observability.

Q: How do I list servers in Pydantic AI?

Simply call metoriallistservers to get an array of your active nodes. It is the best way to verify your infrastructure before deploying new agent logic.

Enforce strict runtime validation for your serverless MCP tools with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Metorial 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 Metorial with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe serverless management

Deploy and manage your infrastructure with `metorial_deploy_server` while relying on Pydantic models to validate every response. If the server returns bad data, your agent throws an error immediately. This prevents silent failures in your production pipelines. You get the benefit of serverless scale with the safety of strict Python typing.

Audit execution logs with Pydantic AI

Use `metorial_list_traces` to review all server-side interactions. Because you are using Pydantic AI, you can map these traces back to your data models to ensure consistency. It turns raw logs into verified data points. You spend less time guessing why a tool failed and more time fixing the logic.

Tool invocation for Pydantic AI agents

Invoke your remote tools using `metorial_invoke_server_tool` within your agent workflows. The server handles the remote execution, while your agent validates the output. It is built for complex, multi-step agent tasks. You define the schema, call the tool, and the system ensures the data matches your requirements before it hits your agent state.

Setup guide

Set up Metorial 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": {
        "metorial-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Metorial 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 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 Pydantic AI

Pydantic AI validates every response against your models at runtime. Combining this with Metorial ensures that even remote serverless outputs are strictly typed and safe.

Use the MCPToolset class with your HTTP endpoint. It works with both Streamable HTTP and SSE transports, making it easy to link your Pydantic AI agent to the server.

Call `metorial_get_usage_metrics` to see your current latency and cost data. It integrates into your Pydantic AI workflow to provide real-time observability.

Simply call `metorial_list_servers` to get an array of your active nodes. It is the best way to verify your infrastructure before deploying new agent logic.

We enforce strict zero-trust boundaries around your serverless execution logs. Your data is restricted to your authenticated environment, ensuring no unauthorized access to your server traces.

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