How to Use the Convoy MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK automatically retry failed Convoy deliveries?

Yes, by using the batchretryeventdeliveries tool. The agent queries delivery logs, identifies the failures, and triggers a batch retry programmatically.

Q: Can the agent create custom filters for webhook subscriptions?

Yes, the agent uses bulkcreatefilters to set up routing rules. This lets your OpenAI client dynamically filter out unwanted payloads before they reach downstream endpoints.

Let OpenAI Agents SDK build and manage webhook endpoints safely using Convoy tools with direct execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convoy MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Convoy endpoints with OpenAI Agents SDK

The `create_endpoint` tool lets your agent configure a new webhook destination whenever a user requests a new integration. Your OpenAI client handles the schema setup and registers the target URL in Convoy without you writing custom API routes. If an endpoint misbehaves, the agent calls `pause_endpoint` to halt traffic immediately. This keeps your production system stable during downstream outages by pausing delivery runs before errors cascade.

Broadcast messages to thousands of targets

The `broadcast_event` tool sends a payload to all active subscriptions configured in your Convoy instance. Your OpenAI Agents SDK maps the user input to the correct payload format and initiates the broadcast. For targeted delivery, the agent runs `fanout_event` to distribute payloads based on subscription rules. This lets your agent manage complex routing topologies without hardcoded routing tables.

Debug failing webhooks inside your agent loop

The `list_delivery_attempts` tool exposes the exact HTTP response codes and payloads of failed attempts directly to your agent via the MCP Server. When a webhook fails, the OpenAI Agents SDK reads these logs to diagnose the issue. Once the agent identifies the failure cause, it executes `retry_event_delivery` to resend the payload. This automates support tasks like fixing bad endpoints and re-running failed deliveries without human intervention.

Setup guide

Set up Convoy 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 Convoy tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip. Pass the server URL to MCPServerStreamableHttpParams and add the streamable HTTP instance to the agent constructor. This MCP integration lets your agent auto-discover the 26 tools instantly.

Yes, by using the `batch_retry_event_deliveries` tool. The agent queries delivery logs, identifies the failures, and triggers a batch retry programmatically.

The SDK intercepts 429 errors from the Convoy API. You can write custom guardrails in your agent definition to pause calls to `create_event` when rate limits are hit.

Yes, the agent uses `bulk_create_filters` to set up routing rules. This lets your OpenAI client dynamically filter out unwanted payloads before they reach downstream endpoints.

All delivery logs and payload data stay within the V8 Isolate Sandbox on Vinkius. The MCP Server communicates over encrypted HTTPS channels, ensuring your OpenAI client never exposes raw webhook secrets during 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