How to Use the Treblle MCP in Pydantic AI

Q: Can Treblle mask SSNs when working with Pydantic AI?

Yes. The ingestapidata tool masks Social Security Numbers (SSNs) automatically, ensuring sensitive data remains protected during monitoring.

Validated API Observability for Pydantic AI Agents

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Treblle MCP to Pydantic AI

Create your Vinkius account to connect Treblle 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 Treblle with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor API Traffic with Treblle MCP Server

The `ingest_api_data` tool lets your agent monitor, document, and analyze live API traffic. You feed it request and response data, getting instant observability into the underlying calls. This is key for type-safe systems; you track exactly what payload came in and what was returned.

Secure Data Ingestion into Pydantic AI

Treblle automatically masks sensitive data before it gets logged. When using `ingest_api_data`, the server handles passwords, CCs, and SSNs. This means that even when your agent fails loudly due to validation errors, the underlying logs remain secure.

Real-Time API Documenting for Pydantic AI

You get instant documentation of API calls using `ingest_api_data`. It ingests request and response data streams as they happen, supporting type validation. This immediate visibility lets you correlate unexpected agent failures with specific payload anomalies.

Setup guide

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

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

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

Treblle automatically masks passwords, CCs, and SSNs before they are transmitted or logged. This keeps your observed API traffic compliant with strict data handling rules.

It provides real-time monitoring and documentation, analyzing both request and response data in the background. You get full visibility into the API calls your agent makes.

Yes. The `ingest_api_data` tool masks Social Security Numbers (SSNs) automatically, ensuring sensitive data remains protected during monitoring.

It does. The server ingests and documents live traffic streams immediately, which is crucial when debugging type validation failures.

The server handles passwords, credit card numbers (CCs), and Social Security Numbers (SSNs). All these fields are masked before they reach your agent's validation scope.

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