How to Use the Dripcel MCP in OpenAI Agents SDK

Q: Can I use OpenAI Agents SDK guardrails to restrict Dripcel message templates?

Yes. You can configure the SDK to intercept calls to sendwhatsappmessage and validate them against the templates returned by listwhatsapptemplates. This prevents your agent from sending unapproved, free-form text that might trigger WhatsApp spam filters.

Q: Why should I set cacheToolsList to True with Dripcel in the OpenAI Agents SDK?

Setting cacheToolsList=True in your OpenAI Agents SDK setup stops the SDK from repeatedly querying the Dripcel MCP server for its tool definitions. It speeds up agent execution times when running high-frequency tasks like calling quickinstancehealthaudit across dozens of phone instances.

Q: How do I handle agent handoffs when querying WhatsApp contacts?

You set up one agent dedicated to searching contacts via searchinstancecontacts and another for reading histories with listwhatsappmessages. The SDK manages the handoff, passing the context and the shared Dripcel connection between them.

Trigger WhatsApp campaigns and audit connection health directly from your OpenAI Agents SDK workflow.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dripcel MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe WhatsApp dispatch via OpenAI Agents SDK

Your agent needs to talk to customers without breaking API rules. By feeding `send_whatsapp_message` directly into the OpenAI Agents SDK, you let your agent send texts while the framework's guardrails block bad payloads before they hit the wire. Tracking these automated runs gets simple. The SDK sends execution logs straight to your OpenAI dashboard, showing you exactly when the agent calls `get_whatsapp_templates` to fetch approved templates or fires off a message.

Automated contact lookups with agent handoffs

Stop writing manual routing logic for customer lookups. Let a specialized triage agent use `search_instance_contacts` to find a customer, then hand the conversation off to a messaging agent that pulls their history with `list_whatsapp_messages`. The OpenAI Agents SDK handles these handoffs natively. Because you initialize the Dripcel MCP server with `MCPServerStreamableHttp`, both agents share access to `list_instance_contacts` to keep customer profiles updated.

Proactive connection auditing and safety

Dead connections kill campaigns. Fix this by letting a background agent run `quick_instance_health_audit` to check if your WhatsApp numbers are online before running high-volume outreach. If a number drops, the agent uses `get_whatsapp_connection_status` to pinpoint the failure. The OpenAI Agents SDK lets you cache this tool list using `cacheToolsList=True` so your monitoring loops run fast without burning API cycles.

Setup guide

Set up Dripcel 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 Dripcel tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using pip, then initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when creating your Agent, and the SDK will auto-discover tools like `send_whatsapp_message` with zero extra configuration.

Yes. You can configure the SDK to intercept calls to `send_whatsapp_message` and validate them against the templates returned by `list_whatsapp_templates`. This prevents your agent from sending unapproved, free-form text that might trigger WhatsApp spam filters.

Setting `cacheToolsList=True` in your OpenAI Agents SDK setup stops the SDK from repeatedly querying the Dripcel MCP server for its tool definitions. It speeds up agent execution times when running high-frequency tasks like calling `quick_instance_health_audit` across dozens of phone instances.

You set up one agent dedicated to searching contacts via `search_instance_contacts` and another for reading histories with `list_whatsapp_messages`. The SDK manages the handoff, passing the context and the shared Dripcel connection between them.

The SDK never sees your raw WhatsApp session tokens or Dripcel API keys. All authentication is isolated inside the Vinkius V8 sandbox, meaning your agent only interacts with safe tool schemas like `get_instance_details` without exposing raw credentials to the LLM.

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