How to Use the FreeClimb MCP in OpenAI Agents SDK

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

Install the openai-agents package. Create an MCPServerStreamableHttp instance pointing to your MCP server endpoint. Pass it via the mcpservers array in your Agent constructor.

Q: Can FreeClimb and the OpenAI Agents SDK handle live call routing?

Yes. Your agent reads active sessions using listconferences. It can trigger handoffs between specialized agents based on the caller's input.

Q: Does the OpenAI Agents SDK cache FreeClimb tools?

Set cacheToolsList=True when initializing the server. This stops the agent from pulling the schema for makecall and sendsms on every single invocation.

Give your OpenAI Agents SDK production voice and SMS capabilities.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FreeClimb MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Outbound voice for OpenAI Agents SDK

You need your agent to pick up the phone. Passing the `make_call` tool to your OpenAI agent lets it dial out to customers directly. The agent evaluates the prompt, checks the guardrails you defined, and initiates the call without human intervention. Managing live calls requires context. Your agent can pull active sessions using `list_conferences` and check past interactions with `list_calls` and `get_call_details`. If a handoff to a specialized agent is triggered, the new agent immediately reads the call history before speaking.

Two-way SMS via this MCP Server

Texting is the highest conversion channel you have. This MCP Server exposes `send_sms` directly to your agent system. It formats the payload, hits the FreeClimb API, and fires off the message. You cannot just blast texts and hope for the best. The agent uses `list_sms_messages` and `get_sms_details` to verify delivery status. OpenAI's tracing dashboard logs every single message attempt so you know exactly what your bot sent.

Automated number provisioning

Scaling local presence means buying numbers in specific area codes. Your agent queries `list_buyable_numbers` to find available inventory. It evaluates the options and provisions what you need. You keep track of your assets with `list_my_numbers`. Before running a massive outbound campaign, the agent pulls `get_account_status` to ensure you have the balance to support it. Runaway bot loops drain accounts fast.

Setup guide

Set up FreeClimb 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 FreeClimb tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the `openai-agents` package. Create an `MCPServerStreamableHttp` instance pointing to your MCP server endpoint. Pass it via the `mcp_servers` array in your Agent constructor.

Yes. Your agent reads active sessions using `list_conferences`. It can trigger handoffs between specialized agents based on the caller's input.

Set `cacheToolsList=True` when initializing the server. This stops the agent from pulling the schema for `make_call` and `send_sms` on every single invocation.

Use the built-in guardrails. You define strict rules before execution to cap how many times `send_sms` fires per session.

The server touches sensitive phone numbers and SMS message content. Vinkius isolates the integration in an ephemeral V8 sandbox. Zero-trust architecture guarantees the agent only reads the data it specifically requests, and the container dies immediately after execution.

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