How to Use the Ironclad MCP in OpenAI Agents SDK

Q: How does the agent know which contract template to use?

Your agent runs ironcladlisttemplates to retrieve the active schema of all available contract types. It then maps the incoming sales data to the required template fields before launching.

Q: Can we monitor live contract changes and webhooks?

Yes, you can use ironcladlistwebhooks to inspect registered endpoints. This helps verify that your external systems receive immediate alerts when a contract state changes.

Q: How do I configure the Ironclad MCP Server inside the OpenAI Agents SDK?

Install via pip install openai-agents and initialize the server using MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass the server instance directly into your Agent constructor with cacheToolsList=True to keep tool discovery fast and efficient.

Q: Can an OpenAI Agents SDK agent handle multiple concurrent Ironclad workflows?

Yes, the agent uses ironcladlistworkflows to pull all active contract lifecycles. It can process these in parallel, checking statuses and updating your CRM without getting blocked.

Launch and track Ironclad legal agreements directly from your OpenAI Agents SDK production workflows with zero manual data entry using this 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 Ironclad MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger workflows via OpenAI Agents SDK

The `ironclad_launch_workflow` tool initiates contract generation inside your MCP-driven legal pipeline using pre-approved templates. Your OpenAI Agents SDK setup reads incoming sales deal data, matches it to the right template, and fires off the contract request without human intervention. This setup uses `ironclad_list_templates` to fetch valid template identifiers before execution. By combining these tools with OpenAI's built-in guardrails, your agent checks that contract values and counterparty names meet compliance rules before starting the drafting phase.

Track pending contract approvals in real time

The `ironclad_get_approvals` tool retrieves the live status of every required internal signer for a specific active contract. When a deal stalls, your agent queries this endpoint to pinpoint the exact person holding up the signature process. Your agent inspects active negotiations by calling `ironclad_get_comments` to pull the latest internal discussions and legal feedback. This lets the OpenAI Agents SDK log precise blocker details directly to your system dashboard, keeping your team updated on legal friction.

Search executed agreements from agent workflows

The `ironclad_search_records` tool scans your contract repository for signed agreements using keywords, dates, or counterparty names. It pulls metadata from completed deals, which allows your agent to answer legal queries instantly using this MCP tool. Once found, `ironclad_get_record` extracts specific obligations and renewal dates from the executed contract. The OpenAI Agents SDK processes these structured fields to flag upcoming expiration dates, preventing missed deadlines without manual spreadsheet lookups.

Setup guide

Set up Ironclad 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 Ironclad tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent runs `ironclad_list_templates` to retrieve the active schema of all available contract types. It then maps the incoming sales data to the required template fields before launching.

Yes, you can use `ironclad_list_webhooks` to inspect registered endpoints. This helps verify that your external systems receive immediate alerts when a contract state changes.

Install via `pip install openai-agents` and initialize the server using `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass the server instance directly into your Agent constructor with `cacheToolsList=True` to keep tool discovery fast and efficient.

Yes, the agent uses `ironclad_list_workflows` to pull all active contract lifecycles. It can process these in parallel, checking statuses and updating your CRM without getting blocked.

Vinkius hosts this server in an ephemeral, zero-trust V8 Isolate Sandbox. Your raw contract files and metadata are never stored on disk, and all API calls use a single, secure endpoint token that keeps your corporate legal data fully isolated.

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