How to Use the Parsio MCP in Pydantic AI

Q: How do I initialize Parsio with Pydantic AI?

Install pydantic-ai-slimmcp, instantiate MCPToolset with your Vinkius HTTP endpoint, and pass it to your Agent constructor's toolsets argument.

Q: Can my Pydantic AI agent run async text extraction with Parsio?

Yes, your agent can trigger extractdatafromtextasync and retrieve the verified schema later using getparseddocumentresult.

Q: How do I check active parsing templates in Pydantic AI?

Have your agent invoke listmailboxtemplates to fetch template metadata, which is automatically validated against your Pydantic models.

Validate extracted Parsio email and PDF data against strict Pydantic models at runtime with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Parsio MCP to Pydantic AI

Create your Vinkius account to connect Parsio 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 Parsio with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Parse files with runtime type safety

Stop worrying about silent extraction failures or corrupt data formats. Your Pydantic AI agent can call `extract_data_from_file_sync` to parse incoming invoices, validating the returned JSON against your strict Pydantic schemas immediately. For larger background tasks, your agent can run `extract_data_from_file_async` to queue the parsing job. The agent polls `get_parsed_document_result` to get the output, ensuring the data matches your defined models before it hits your database.

Discover and validate mailboxes with Pydantic AI

Let your agent inspect your active mailboxes safely using this MCP Server. Just check the outputs of `list_mailboxes` to verify metadata matches the fields your application expects. If your agent needs to create a new ingestion point, it calls `create_mailbox` and receives a typed response. Run this to list active templates via `list_mailbox_templates` so you ensure your agent uses the correct schema for incoming documents.

Audit this MCP Server with type-safe history

Pull historical extraction logs reliably by letting your agent call `list_parsed_data_history`. Pydantic AI validates every past document entry, preventing legacy schema changes from crashing your active agent session. You can also call `list_mailbox_webhooks` to inspect active webhooks. This lets your agent verify data routing paths without risk of parsing malformed webhook configurations.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`, instantiate `MCPToolset` with your Vinkius HTTP endpoint, and pass it to your Agent constructor's `toolsets` argument.

The agent will fail loudly with a validation error rather than silently corrupting your database. This ensures strict schema enforcement for all parsed documents.

Yes, your agent can trigger `extract_data_from_text_async` and retrieve the verified schema later using `get_parsed_document_result`.

Have your agent invoke `list_mailbox_templates` to fetch template metadata, which is automatically validated against your Pydantic models.

Vinkius processes your PDF invoices inside an MCP Server sandbox. This ensures zero-trust execution, and your API keys are never exposed to the LLM or stored in plain text.

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