How to Use the Documint MCP in OpenAI Agents SDK

Q: How do I configure Documint tools in the OpenAI Agents SDK?

Start by installing openai-agents and initializing the MCP Server connection using the streamable HTTP helper. Pass this server instance in the mcpservers list to your Agent constructor, enabling cacheToolsList=True to keep tool discovery fast.

Q: Can I monitor Documint account limits using this setup?

Yes, you can. Have your agent call getdocumintaccountmetadata to check your monthly generation limits and current usage, allowing your pipeline to pause or alert you before hitting caps.

Q: How does this MCP Server protect my PDF templates and generation data?

All document data, including variables sent to createnewgeneration, runs through Vinkius's zero-trust, ephemeral sandbox. This secure MCP setup ensures your Documint API keys and customer PII are never stored on disk.

Generate PDFs from templates inside your OpenAI Agents SDK workflows without leaving your python runtime.

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 OpenAI Agents SDK

Create your Vinkius account to connect Documint to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect Documint Templates with OpenAI Agents SDK

The `list_documint_templates` tool lets your OpenAI Agents SDK coordinate template discovery dynamically before triggering a generation. The agent connects via the MCP Server to locate the target PDF layout, ensuring it grabs the right asset without manual hardcoding. Once it spots the right layout, the agent runs `get_template_configuration` to inspect the exact schema. This allows your agentic workflows to map user inputs directly to Documint's template fields on the fly, avoiding runtime mismatches.

Run Validated Document Generation with Guardrails

The `get_template_variable_audit` tool verifies every required variable is present in the payload before your OpenAI agent executes a generation. This step stops broken payloads from hitting the API, saving you from failed runs and wasted usage. If validation checks out, the OpenAI Agents SDK triggers the document build. The agent monitors the process using `get_generation_details` to grab the download URL, which it can then hand off to downstream storage or notification agents.

Track Generation Status via the OpenAI Dashboard

The `list_latest_doc_generations` tool keeps a clean audit trail of your automated document pipelines directly within your OpenAI tracing logs. This MCP integration lets you poll Documint's generation history to verify successful runs. By feeding this data into the OpenAI Agents SDK monitoring loop, you can build self-healing pipelines. If a run pops up in `list_failed_doc_generations`, your agent can automatically re-parse the payload and retry the generation.

Setup guide

Set up Documint MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Documint tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Documint tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Documint tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Documint Agent",
            instructions="You have access to Documint tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Start by installing `openai-agents` and initializing the MCP Server connection using the streamable HTTP helper. Pass this server instance in the `mcp_servers` list to your `Agent` constructor, enabling `cacheToolsList=True` to keep tool discovery fast.

Yes, by combining OpenAI Agents SDK reasoning with specific auditing tools. The agent can run `get_template_variable_audit` to pinpoint missing fields, fix the payload, and call `create_new_generation` again.

The SDK dynamically fetches schemas at runtime. When templates change in your account, the agent calls `get_template_configuration` to fetch the updated field requirements, adapting its generation payloads instantly.

Yes, you can. Have your agent call `get_documint_account_metadata` to check your monthly generation limits and current usage, allowing your pipeline to pause or alert you before hitting caps.

All document data, including variables sent to `create_new_generation`, runs through Vinkius's zero-trust, ephemeral sandbox. This secure MCP setup ensures your Documint API keys and customer PII are never stored on disk.

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