How to Use the Docamatic MCP in Pydantic AI

Q: How do I integrate the Docamatic MCP server with Pydantic AI?

Install the framework with pip install "pydantic-ai-slimmcp". Then, initialize the MCP server connection using MCPToolset with your Docamatic URL and pass it to the toolsets parameter of your Agent.

Q: Does Docamatic support runtime validation inside Pydantic AI using MCP?

Yes. All parameters passed to tools like generatepdffromtemplate are validated against strict Pydantic models, ensuring your agent never sends bad data to the PDF engine.

Q: Can I use Pydantic AI to merge PDFs generated via Docamatic?

Yes. Your agent can generate multiple documents using generatepdffromhtml and then pass those file paths directly to mergemultiplepdfs for a single, consolidated output.

Q: How do I see what templates are available for my agent to use?

Your agent can call listavailablebuiltintemplates to get a structured list of all pre-designed layouts, such as invoices and packing slips, currently supported by the server.

Run type-safe PDF generation with Pydantic AI and Docamatic, validating every document payload at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docamatic MCP to Pydantic AI

Create your Vinkius account to connect Docamatic 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 Docamatic with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe PDF generation with Pydantic AI

`generate_pdf_from_template` is the core tool that your Pydantic AI agent uses to render structured JSON data into high-fidelity PDFs. Because Pydantic AI enforces type safety, every field injected into your templates is validated before the tool is even executed. This setup guarantees that your agent will never pass malformed data to the rendering engine. If a field is missing or has the wrong type, the agent catches the error immediately, preventing broken PDFs from being generated.

Convert raw HTML and web pages with strict validation

`generate_pdf_from_html` and `take_web_screenshot` are the tools designed to handle dynamic HTML inputs and live website captures. Your agent can convert any raw HTML string into a PDF or capture a full-page screenshot of a URL, with all input parameters validated against strict schemas. This prevents common injection vulnerabilities and ensures the rendering engine only processes safe, well-formed inputs. Your agent can confidently convert complex reports without worrying about silent failures or layout breaks.

Modify and merge PDFs using a secure MCP Server

`merge_multiple_pdfs` and `add_elements_to_pdf` allow your agent to combine multiple documents and draw new text or images onto existing files. Your agent can check the status of these operations by calling `list_generation_history` to verify the output path. The entire process is managed through a single secure endpoint. This eliminates the need to install local PDF libraries or manage complex binary dependencies in your production Python environment.

Setup guide

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

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

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

Install the framework with pip install "pydantic-ai-slim[mcp]". Then, initialize the MCP server connection using MCPToolset with your Docamatic URL and pass it to the toolsets parameter of your Agent.

Yes. All parameters passed to tools like `generate_pdf_from_template` are validated against strict Pydantic models, ensuring your agent never sends bad data to the PDF engine.

Yes. Your agent can generate multiple documents using `generate_pdf_from_html` and then pass those file paths directly to `merge_multiple_pdfs` for a single, consolidated output.

Your agent can call `list_available_builtin_templates` to get a structured list of all pre-designed layouts, such as invoices and packing slips, currently supported by the server.

Yes. Every validated schema, raw HTML string, and output PDF processed by the server is handled inside an isolated, ephemeral V8 sandbox. We do not store your document data, and all connections are fully encrypted.

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