How to Use the Legito MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle Legito template updates?

The SDK queries the live API using listtemplatesuites. When you update a template in your workspace, the agent immediately sees the changes and uses createdocumentversiondata with the new schema.

Q: Can my OpenAI Agents SDK system manage user groups?

Absolutely. Your agent can organize teams by calling createusergroup and addusertogroup. This allows the agent to provision access for entire departments instantly.

Build production-grade Python agents that generate contracts and manage user permissions using the OpenAI Agents SDK and our secure MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Legito MCP to OpenAI Agents SDK

Create your Vinkius account to connect Legito 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 Legito with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Legito contracts using the OpenAI Agents SDK

Your agents can assemble complex legal documents directly inside your python pipelines using `create_document_version_data`. By exposing `list_template_suites`, the agent selects the exact template needed for a deal and populates it. The OpenAI framework traces every step, making sure the agent does not hallucinate fields during generation. You get full visibility into how the agent handles document creation before it hits production. If an agent tries to use an invalid template, your safety guardrails intercept the call. This ensures your legal templates remain pristine and free from corrupt data.

Enforce strict user permissions via MCP Server tools

Managing who sees what contract is a major headache, but you can audit access levels on the fly using `get_user_permissions`. You can write policy agents that automatically run these tools whenever a team member changes roles inside your system. The agent handles the execution, but you retain control. By chaining `share_with_user` and `remove_share_from_user`, your system updates access privileges in real-time. This keeps your document repository secure without requiring manual IT tickets.

Coordinate document handoffs between specialized agents

Complex legal workflows require different agents to handle different tasks, starting with querying document registries via `list_document_records`. One agent can query document registries, while a second specialized agent downloads the file using `download_document_version`. This separation of duties prevents a single agent from having too much control. You configure the handoffs directly in Python. When a contract needs a final review, the first agent passes the document ID to a supervisor agent, which then runs `update_document_record` to change its status. It is a clean, modular way to manage the entire document lifecycle.

Setup guide

Set up Legito 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 Legito tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Legito 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="Legito Agent",
            instructions="You have access to Legito 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 Legito. 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 Legito 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 Legito MCP in OpenAI Agents SDK

Use MCPServerStreamableHttp to connect the server. Pass the endpoint URL and register the toolset inside your agent's constructor. The SDK automatically discovers all 31 tools.

Yes, you can filter tools at the SDK level. If you only want an agent to read data, expose `list_document_records` and `get_document_version_data` while blocking destructive tools like `delete_document_record`.

The SDK queries the live API using `list_template_suites`. When you update a template in your workspace, the agent immediately sees the changes and uses `create_document_version_data` with the new schema.

Absolutely. Your agent can organize teams by calling `create_user_group` and `add_user_to_group`. This allows the agent to provision access for entire departments instantly.

Your document records and binary PDFs never pass through third-party servers. The MCP Server runs inside a secure V8 isolate, executing `download_document_version` directly between your environment and the API.

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