How to Use the Denim MCP in OpenAI Agents SDK

Q: How do I connect Denim to the OpenAI Agents SDK using the MCP specification?

You initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint URL. Pass this instance inside the mcpservers list when instantiating your Agent. Turn on cacheToolsList to keep tool discovery fast and reduce network overhead.

Q: Does Denim support multi-agent handoffs in OpenAI Agents SDK?

It does. You can have one agent use listaudiencesegments to find target groups, then hand off the actual campaign creation to a specialized marketing agent. This keeps your agent architectures clean and modular.

Q: How do I handle rate limits for the Denim MCP server?

The getaccountmetadata tool returns your current API limits and account settings. You should program your agent to check this endpoint periodically. This helps you avoid hitting hard rate limits during high-volume marketing runs.

Control Denim marketing pipelines directly from your production OpenAI Agents SDK setup.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Denim MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run guarded Denim actions using OpenAI Agents SDK

The `add_new_contact` tool inserts new leads directly into your Denim database from incoming agent conversations. Your OpenAI agent processes the chat, extracts the lead details, and executes this tool safely within your defined parameters. You get full execution tracing inside your OpenAI dashboard. This means you can spot failed imports or bad inputs instantly without digging through raw server logs.

Track campaign performance directly in Python

The `get_campaign_analytics` tool pulls real-time performance metrics for any active marketing push. Your agent parses this data to decide if a campaign needs adjustments or if budget should be reallocated. By pairing this with `get_campaign_details`, your script inspects the actual settings of your run. It gives your automated systems the ground truth they need to make smart decisions.

Audit your active automation workflows

The `list_active_automations` tool retrieves every active marketing workflow currently running in your Denim account. Your agent reads this list to ensure no duplicate campaigns target the same audience. We built this to prevent embarrassing double-emails to your customers. Our MCP implementation acts as a safety check before your agent triggers any new outgoing sequences.

Setup guide

Set up Denim 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 Denim tools at runtime.
3

Create your Agent

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

Run the agent

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

You initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass this instance inside the `mcp_servers` list when instantiating your Agent. Turn on `cacheToolsList` to keep tool discovery fast and reduce network overhead.

Yes, the SDK enforces built-in guardrails that check tool arguments before they hit your Denim database. If an agent tries to send an invalid email format to `add_new_contact`, the SDK catches it. This prevents junk data from polluting your marketing lists.

It does. You can have one agent use `list_audience_segments` to find target groups, then hand off the actual campaign creation to a specialized marketing agent. This keeps your agent architectures clean and modular.

The `get_account_metadata` tool returns your current API limits and account settings. You should program your agent to check this endpoint periodically. This helps you avoid hitting hard rate limits during high-volume marketing runs.

All contact details, emails, and campaign analytics are transmitted through secure, encrypted Vinkius tunnels. We run your server inside an isolated V8 sandbox that forgets all session data the moment the execution finishes. Your customer database remains completely private.

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