How to Use the Sensible MCP in Pydantic AI

Q: Can I delete old configurations?

Yes, use deleteconfiguration to prune your environment. This keeps your workspace clean and reduces the chance of using outdated parsing logic.

Get type-safe document extraction for your Pydantic AI agents with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sensible MCP to Pydantic AI

Create your Vinkius account to connect Sensible to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sensible with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe Extraction Results

Ensure your agent only acts on valid data by using the structured output from `extract_sync_with_config`. Because Pydantic AI validates every response, you get immediate errors if the parser returns unexpected fields. This prevents silent data corruption. You can map the output directly to your Pydantic models for strict runtime verification.

Golden Reference Management

Improve your parsing accuracy by creating reference documents with `create_golden`. These act as the source of truth for your configuration training. You can list and update these references as document layouts shift. This keeps your parsing logic locked to high-quality examples.

Granular Configuration Access

Query specific parsing rules using `get_configuration` or `list_configurations`. This allows your agent to inspect its own capabilities before attempting a complex extraction. It makes your agent's decision-making process transparent. You can programmatically switch configurations if a specific document type requires a unique approach.

Setup guide

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

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

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

Yes, every tool response is structured JSON. You can define a Pydantic model to enforce the schema on the data returned by the server.

If the parser returns data that doesn't match your model, Pydantic AI will throw a validation error. This forces your agent to handle the failure explicitly.

It is built for developers who prioritize correctness. The combination of schema-based configurations and type-safe agents minimizes hallucination risks.

Yes, use `delete_configuration` to prune your environment. This keeps your workspace clean and reduces the chance of using outdated parsing logic.

All documents are handled via pre-signed URLs or base64 strings. No raw files are persisted beyond the immediate processing window.

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