How to Use the Documint MCP in Pydantic AI

Q: How do I register the Documint MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and initialize your MCP Server connection using the HTTP toolset helper. Pass the toolset object directly into the toolsets list when configuring your Agent instance.

Q: How does Pydantic AI handle unexpected data from Documint?

If an API call like getgenerationdetails returns data that violates your defined schemas, Pydantic AI raises a validation error immediately, protecting your code from processing corrupt PDF URLs.

Q: Can Pydantic AI search for Documint templates dynamically?

Yes, the agent can run searchdocuminttemplates or listdocuminttemplates to locate specific layouts, then validate the resulting template IDs before proceeding with generation.

Q: How do I check my Documint account status using Pydantic AI?

Your agent can call getdocumintaccountmetadata to retrieve your account's plan details and current generation volume, returned as a fully validated, type-safe Python object.

Build type-safe document generation pipelines with Pydantic AI and Documint.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Documint MCP to Pydantic AI

Create your Vinkius account to connect Documint 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 Documint with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Documint Templates at Runtime with Pydantic AI

The `get_template_configuration` tool prevents silent PDF rendering failures by fetching the exact schema of your Documint templates to validate against your local Python models. This MCP Server integration allows your Pydantic AI agent to inspect field types dynamically before sending payload requests. By feeding this schema into the Pydantic AI runtime, the agent ensures that every field required by `create_new_generation` matches your data types. If a field is missing, the agent triggers a validation error immediately instead of sending bad data to the API.

Audit Document Variables Dynamically

The `get_template_variable_audit` tool keeps your template integration secure and up to date by identifying the required variables for any given template. This dynamic auditing allows your Pydantic AI agent to handle template changes gracefully. If a marketing team adds a new field to a Documint template, your agent detects the change and updates its validation schemas automatically. This keeps your generation pipelines from breaking when layouts shift.

Track and Debug Document Generation Runs

The `list_documint_generations` tool maintains strict control over your document outputs by tracking the state of every PDF. The agent queries this MCP tool to return typed responses that your application can safely parse. When errors occur, the agent calls `list_failed_doc_generations` to capture failures and map them to custom error models. This ensures your Pydantic AI application can handle API errors gracefully without crashing your production environment.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and initialize your MCP Server connection using the HTTP toolset helper. Pass the toolset object directly into the `toolsets` list when configuring your `Agent` instance.

If an API call like `get_generation_details` returns data that violates your defined schemas, Pydantic AI raises a validation error immediately, protecting your code from processing corrupt PDF URLs.

Yes, the agent can run `search_documint_templates` or `list_documint_templates` to locate specific layouts, then validate the resulting template IDs before proceeding with generation.

Your agent can call `get_documint_account_metadata` to retrieve your account's plan details and current generation volume, returned as a fully validated, type-safe Python object.

All payloads containing sensitive template variables are transmitted over encrypted SSE or HTTP connections directly to Documint's secure endpoints. The Vinkius MCP sandbox acts as a pass-through layer, ensuring no customer data is logged or retained.

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