How to Use the Aporia MCP in Pydantic AI

Q: How do I configure Aporia with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to the HTTP endpoint and pass it to your Agent's toolsets array.

Connect Aporia to Pydantic AI to validate LLM safety checks with strict, type-safe runtime constraints.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aporia MCP to Pydantic AI

Create your Vinkius account to connect Aporia 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 Aporia with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe guardrails for Pydantic AI

The `validate_guardrails` tool intercepts your agent's message arrays to check for toxicity and PII leaks. It returns structured validation data that Pydantic AI strictly enforces at runtime. If the LLM tries to bypass a safety rule, the framework fails loudly. This MCP Server ensures bad outputs trigger immediate validation errors, preventing silent data corruption in your production pipelines.

Fetch drift metrics dynamically

The `get_metrics` tool pulls live drift and performance statistics for any tracked model. You pair this with `get_model` to verify the exact parameters of the model currently in use. Your agent uses these numbers to decide if it should trust the current model. If the drift exceeds your Pydantic thresholds, the system halts the operation and alerts your engineering team.

Trigger Aporia monitors instantly

The `trigger_monitor` tool forces an immediate execution of a specific safety monitor. You can map out your entire workspace observability setup using `list_monitors` and `list_dashboards`. This gives your agent active control over its own oversight. Instead of waiting for a cron job, the agent fires a monitor run the second it detects an ambiguous input, guaranteeing real-time safety.

Setup guide

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

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

result = await agent.run("List recent Aporia 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 Aporia. 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 Aporia 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 Aporia MCP in Pydantic AI

Install pydantic-ai-slim[mcp]. Create an MCPToolset pointing to the HTTP endpoint and pass it to your Agent's toolsets array.

Pydantic AI enforces strict schemas. When Aporia flags an interaction as toxic, the framework immediately throws a validation error, stopping the agent dead.

Completely. Whether you run local models or cloud APIs, the MCP Server validates the text output itself, not the model weights.

Yes. The unified toolset approach in Pydantic AI supports both Streamable HTTP and SSE transports for any external MCP Server.

The server processes the specific prompt and completion text you pass to the validation tool. It scans for sensitive information in memory to return a pass/fail state and does not store your application's data.

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