How to Use the Chiirp MCP in OpenAI Agents SDK

Q: How do OpenAI Agents SDK tools auto-discover Chiirp MCP actions?

You pass the chiirp-mcp HTTP URL to the MCPServerStreamableHttp constructor. The OpenAI Agents SDK automatically queries the server's manifest, instantly exposing tools like listcontacts and searchcontacts to your agent without manual configuration.

Q: How does OpenAI Agents SDK handle Chiirp campaign list caching over MCP?

By setting cacheToolsList=True in your OpenAI Agents SDK configuration, you prevent the agent from repeatedly querying the schema. This speeds up calls to Chiirp's listcampaigns and listsequences during active user sessions.

Q: What happens if a Chiirp contact search fails?

The searchcontacts tool returns a structured error to the SDK. Your OpenAI agent reads this failure, logs the event in the tracing dashboard, and can transition to the createcontact tool to register the new lead.

Run production-ready OpenAI Agents with automated safety guards around your Chiirp text and email marketing pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chiirp MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe contact creation with OpenAI Agents SDK

The `create_contact` tool registers new prospects in Chiirp using their phone number as a unique identifier. When you run this tool within the OpenAI Agents SDK, the framework's built-in guardrails validate the phone number format before the agent can execute the payload. This prevents your autonomous agent from sending malformed data to your SMS campaigns. You can monitor these validation checks directly in your OpenAI developer dashboard. If a user provides an invalid number, the agent catches the error at the boundary, allowing your system to request correction without wasting API credits or risking compliance issues.

Multi-agent tag routing using this MCP Server

The `apply_tag` and `remove_tag` tools let your system segment contacts based on conversation context. By deploying specialized OpenAI agents, you can have one agent analyze chat sentiment and another handle the actual tag updates. The SDK handles the handoff between these agents without requiring you to write custom state-machine code. Once a tag is applied, Chiirp triggers its internal automation sequences. The transition is tracked in real-time, meaning you get a clean audit trail of which agent applied which tag and why, keeping your marketing lists accurate.

Campaign status checks with OpenAI Agents SDK

The `check_chiirp_status` tool verifies your API connectivity before your agent initiates complex marketing operations using this MCP Server. Using the SDK's async context manager, your agent checks the connection health at startup to avoid runtime failures during high-volume outreach. If the server is unreachable, the agent pauses execution. This prevents the system from attempting to read campaigns via `list_campaigns` or trigger sequences with `list_sequences` when the underlying service is offline.

Setup guide

Set up Chiirp 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 Chiirp tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass the `chiirp-mcp` HTTP URL to the `MCPServerStreamableHttp` constructor. The OpenAI Agents SDK automatically queries the server's manifest, instantly exposing tools like `list_contacts` and `search_contacts` to your agent without manual configuration.

Yes, you can define input validation schemas in your agent definition. This ensures that when the agent calls `apply_tag`, the tag name matches your pre-approved list before the SDK executes the call.

By setting `cacheToolsList=True` in your OpenAI Agents SDK configuration, you prevent the agent from repeatedly querying the schema. This speeds up calls to Chiirp's `list_campaigns` and `list_sequences` during active user sessions.

The `search_contacts` tool returns a structured error to the SDK. Your OpenAI agent reads this failure, logs the event in the tracing dashboard, and can transition to the `create_contact` tool to register the new lead.

Vinkius runs the Chiirp MCP Server in an ephemeral V8 Isolate sandbox, meaning no contact phone numbers or profiles are stored on our servers. Your OpenAI Agents SDK connects directly via a secure endpoint token, keeping your customer database 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