Does this tool parse the document directly or use the cloud engine?

The tool offloads the logic specifically via endpoints mapping back to the Parseur Cloud Engine. The AI acts to organize mailboxes, list templates, and fetch final states securely without computing massive local OCR networks.

Can I upload a raw file string to be parsed?

Yes. Utilizing the explicitly mapped `upload_document` constraint, the agent can inject raw string boundaries identifying formatting, passing files straightforward into the target mailbox ID natively.

Will I see missing required fields if extraction fails?

Absolutely. Querying `get_document_details` lists specific status bounds. If a template expects InvoiceTotal and misses it, the document flags a processing boundary issue precisely traceable here.

Parseur MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Parseur
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Parseur through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Parseur "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Parseur?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Parseur MCP Server

Bring Parseur Document Extraction arrays directly into your AI workflows. By explicitly mapping into powerful OCR and templating engines, your agent can push unstructured PDFs or bulk emails into remote routing limits, parsing exact text fields securely. Extract fields, examine documents, list defined parse-templates, and retry pipelines without manual intervention.

Pydantic AI validates every Parseur tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Mailboxes & Templates — Examine specifically bound mailboxes tracking which explicit templates dictate data extraction limits mapped natively
Document Navigation — Extract properties showing precisely which unstructured strings were identified inside uploaded payloads checking status: parsed correctly
Payload Uploading — Instruct the node limits mapping upload_document generating raw payloads routing straight into the engine for OCR logic
Job Management — Discover disconnected states mitigating failed validations by pushing retry_document instantly forcing physical pipeline resets

The Parseur MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Parseur to Pydantic AI via MCP

Follow these steps to integrate the Parseur MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Parseur with type-safe schemas

Why Use Pydantic AI with the Parseur MCP Server

Pydantic AI provides unique advantages when paired with Parseur through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Parseur integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Parseur connection logic from agent behavior for testable, maintainable code

Parseur + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Parseur MCP Server delivers measurable value.

Type-safe data pipelines: query Parseur with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Parseur tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Parseur and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Parseur responses and write comprehensive agent tests

Parseur MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Parseur to Pydantic AI via MCP:

create_mailbox

The type determines the parsing engine (e.g., "pdf", "email", "attachment"). Once created, you can configure templates and forward documents to the mailbox for automatic extraction. Create a new Parseur mailbox for document parsing

create_template

Pass the template name and a JSON config string defining field mappings. Parseur will use this template to extract structured data from matching documents. Create a new extraction template for a Parseur mailbox

get_document_data

Fields depend on the template configuration (e.g., invoice_number, total_amount, line_items). Only works for documents with status "processed". Retrieve the fully extracted JSON data from a parsed document

get_document_details

Does not include the parsed data itself — use get_document_data for that. Get metadata of a single parsed document

get_mailbox

Use this to verify mailbox setup before sending documents. Get detailed configuration of a specific Parseur mailbox

list_documents

Each entry includes document ID, status (processed, failed, pending), and metadata like sender and received date. List all parsed documents inside a Parseur mailbox

list_mailboxes

Each mailbox represents a parsing pipeline for a specific document type (invoices, receipts, emails). Use the returned mailbox IDs for subsequent operations like listing documents or uploading files. List all Parseur parsing mailboxes

list_templates

Templates define the extraction rules (field names, locations, regex patterns) used to pull structured data from incoming documents. List available extraction templates for a Parseur mailbox

retry_document

Useful after fixing template rules or when the original parse failed due to a transient error. The document will be matched against the latest template rules. Retry parsing a failed or errored Parseur document

upload_document

eml) to the specified mailbox for automatic parsing. The document enters the processing queue and will be parsed according to the mailbox template. Returns the new document ID for tracking. Upload a document URL to a Parseur mailbox for parsing

Example Prompts for Parseur in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Parseur immediately.

"Check my Parseur mailboxes to find the specific bounding IDs."

"Get the data schema parsed tightly inside document doc_987."

"Upload this snippet of parsed text directly into Mailbox xyz12 for OCR processing."

Troubleshooting Parseur MCP Server with Pydantic AI

Common issues when connecting Parseur to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Parseur + Pydantic AI FAQ

Common questions about integrating Parseur MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Parseur MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.