How to Use the Clickatell MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK cache Clickatell MCP Server tools?

Yes, you want to set cacheToolsList=True for better performance. This prevents the agent from fetching the schema on every single execution loop.

Q: Which tool checks available funds before sending?

Call getaccountbalance to retrieve cloud metrics on your funding limits. Your agent should run this before attempting large bulk dispatches.

Build production messaging agents with OpenAI Agents SDK and Clickatell.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clickatell MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe SMS Dispatch with OpenAI Agents SDK

Your deployed agents need strict boundaries before firing off thousands of texts. Using the OpenAI Agents SDK guardrails, you can intercept `dispatch_bulk_sms` calls to validate target numbers against your internal opt-out lists. The built-in tracing lets you watch exactly how the agent builds the JSON payload before it hits the Clickatell MCP Server. Handoffs make this even better. You might have a specialized billing agent that checks `get_account_balance` first. If funds are low, it hands control to a notification agent rather than failing a massive `dispatch_sms_message` run mid-execution.

Track Carrier Delivery Without Polling

Production systems die when agents get stuck in endless polling loops. Instead of writing custom retry logic, your agent hits `get_delivery_status` only when triggered by an incoming webhook. The OpenAI dashboard captures every carrier property extracted during the check. You can also verify routes before wasting money. Calling `test_carrier_coverage` lets your agent confirm MSISDN routing paths. If a route fails, the agent immediately logs the error and halts the campaign.

Dynamic Inbound Rule Management

Hardcoding webhook endpoints is a terrible idea for autonomous systems. Your agent can dynamically map HTTP logic bounds by calling `upsert_inbound_rule` through this MCP Server when spinning up new campaign environments. When the marketing push ends, it cleans up after itself with `wipe_inbound_rule`. Scheduled drops get the same treatment. The agent queries `list_scheduled_campaigns` to find active arrays spanning your marketing boundaries. If a critical typo is found, it executes `cancel_queued_message` to vaporize the block before the texts actually send.

Setup guide

Set up Clickatell 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 Clickatell tools at runtime.
3

Create your Agent

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

Run the agent

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

Pass the Vinkius MCP endpoint token into your setup. You instantiate `MCPServerStreamableHttp` with your URL and hand it to the Agent constructor via the `mcp_servers` parameter. Tools auto-discover immediately.

Yes, you want to set `cacheToolsList=True` for better performance. This prevents the agent from fetching the schema on every single execution loop.

The API returns the exact error code back to your agent. Built-in tracing captures the failure in your OpenAI dashboard so you can debug the exact payload.

Call `get_account_balance` to retrieve cloud metrics on your funding limits. Your agent should run this before attempting large bulk dispatches.

MSISDN routes and text message contents never touch disk. The Vinkius V8 Isolate Sandbox processes your Clickatell credentials and payload data in memory, destroying the environment the millisecond the request finishes.

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