How to Use the CallFire MCP in OpenAI Agents SDK

Q: How do I connect CallFire to the OpenAI Agents SDK?

Use MCPServerStreamableHttp pointing to your Vinkius endpoint token. Pass it in the mcpservers array when initializing your Agent. Set cacheToolsList=True to speed up startup times.

Q: How do I track failed SMS messages?

Have your agent run listsentsms on a schedule. It can filter the results and extract delivery failures directly from the API response.

Build production messaging agents with OpenAI Agents SDK to send SMS and trigger voice calls automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallFire MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger campaigns via OpenAI Agents SDK

This CallFire MCP server exposes the `send_sms` and `send_voice_call` tools directly to your OpenAI agent system. Hand off the task to a specialized communications agent, and it fires the text or call without human intervention. Guardrails catch bad formatting before execution. The SDK validates the phone numbers and payload structure before passing them to the MCP Server. You get full tracing in the OpenAI dashboard when an agent decides to initiate contact.

Automated Campaign Monitoring

Give your agent access to `list_calls` and `list_sent_sms` to track outbound metrics automatically. It pulls the exact delivery status and duration metrics into its context window. Deep dives happen instantly. When a specific interaction fails, the agent uses `get_call_details` or `get_sms_details` to pull the error codes. Handoffs let a reporting agent aggregate this data while your messaging agent keeps processing the queue.

Account & Asset Management

The `list_campaign_sounds` tool lets your agent fetch pre-recorded audio files before firing off a broadcast. It checks available `list_keywords` to assign the right rented number to the campaign. Running out of credits stops production systems cold. Your agent can hit `get_account_info` to monitor balances and active webhooks via `list_webhooks`. If the balance drops, the agent can trigger an alert through your existing infrastructure.

Setup guide

Set up CallFire 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 CallFire tools at runtime.
3

Create your Agent

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

Run the agent

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

Use `MCPServerStreamableHttp` pointing to your Vinkius endpoint token. Pass it in the `mcp_servers` array when initializing your Agent. Set `cacheToolsList=True` to speed up startup times.

Yes. The SDK automatically reads the tool definitions from the MCP server. You don't write any custom schemas for things like `send_sms` or `list_webhooks`.

Perfectly. Specialized agents can handle the communication layer. You might build one agent for database queries that hands off phone numbers to a dedicated CallFire agent for the actual broadcast.

Have your agent run `list_sent_sms` on a schedule. It can filter the results and extract delivery failures directly from the API response.

Vinkius isolates your CallFire MCP connection in an ephemeral V8 sandbox. Phone numbers, campaign sounds, and SMS contents only exist in memory during the OpenAI Agents SDK execution. The sandbox is destroyed the moment the token expires.

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