How to Use the Convoy MCP in AutoGen

Q: How do AutoGen agents collaborate to retry failed Convoy deliveries?

A monitoring agent detects failures via listeventdeliveries and alerts a debugging agent. They negotiate the retry strategy and call retryeventdelivery once they agree on the cause.

Q: Can AutoGen agents create portal links for Convoy?

Yes, a support agent can invoke createportallink during a conversation with a user. This generates a secure URL the user can access to inspect their own webhook delivery logs.

Deploy AutoGen agents that debate, verify, and execute Convoy webhook configurations.

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 AutoGen

Create your Vinkius account to connect Convoy to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Webhook Onboarding in AutoGen

`bulk_onboard` executes after your AutoGen developer and security agents reach consensus on endpoint validation. One agent drafts the endpoint parameters, another checks for security compliance, and a third executes the tool. This multi-agent debate prevents misconfigured endpoints from entering production. The agents negotiate routing rules before calling `create_subscription` to bind the new destinations.

Multi-Agent Webhook Incident Response via MCP Server

`pause_endpoint` is invoked by a monitoring agent when webhook delivery failure rates spike. A separate debugging agent then analyzes the failure logs using this MCP Server. Once the debugging agent identifies the root cause, it coordinates with the operator agent to run `batch_retry_event_deliveries`. The endpoint is only reactivated via `activate_endpoint` after all agents agree the target is stable.

Collaborative Event Broadcasting

`broadcast_event` sends payloads across your system after your content validation agents sign off on the data. The agents check payload schemas against registered event types before triggering the broadcast. If validation fails, the agents collaborate to rewrite the payload structure on the fly. They then call `create_event` to dispatch the corrected webhook to the target endpoints.

Setup guide

Set up Convoy MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Convoy tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Convoy_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Convoy data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Convoy_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Convoy data")
    print(result.messages[-1].content)

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 AutoGen

A monitoring agent detects failures via `list_event_deliveries` and alerts a debugging agent. They negotiate the retry strategy and call `retry_event_delivery` once they agree on the cause.

Yes, your routing agent determines the filter criteria and passes them to a configuration agent. That agent then calls `create_filter` to apply the rules to the subscription.

Vinkius manages the API keys behind a single secure endpoint token. Your AutoGen agents simply call the tools without needing access to your raw Convoy credentials.

Yes, a support agent can invoke `create_portal_link` during a conversation with a user. This generates a secure URL the user can access to inspect their own webhook delivery logs.

It remains securely on your Convoy instance. Vinkius runs the server in an ephemeral MCP sandbox, meaning configuration details retrieved via `get_endpoint` are never stored permanently.

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