How to Use the Convoy MCP in CrewAI

Q: How does CrewAI handle rate limits when calling Convoy tools?

If your crew triggers too many calls to fanoutevent or createevent, the Convoy API may return rate limit headers. You must handle these 429 responses in your CrewAI task definitions to prevent the agents from looping.

Deploy autonomous agent teams to monitor and repair Convoy webhooks within CrewAI.

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 CrewAI

Create your Vinkius account to connect Convoy to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Incident Response in CrewAI

CrewAI lets you run a specialized team where one agent monitors delivery health and another takes action. The monitoring agent calls `list_event_deliveries` to find failing webhooks, then hands the payload over to the responder agent. The responder agent uses `get_delivery_attempt` to diagnose the issue. If it is a transient server error, the agent executes `retry_event_delivery` to fix it, or triggers `batch_retry_event_deliveries` if multiple messages are stuck.

Autonomous Portal Management via MCP Server

Let your agents manage customer access without writing manual portal code. This MCP Server lets your customer success agent call `create_portal_link` to generate secure, temporary dashboard links for users who need to debug their own webhooks. The agent can verify the customer's endpoint status using `get_endpoint` before sending the link. This allows your CrewAI team to handle support requests end-to-end without human developers getting involved.

Intelligent Event Broadcasting

When your system triggers a critical state change, your CrewAI agents can coordinate to broadcast it. An agent analyzes the state change and uses `broadcast_event` to push the update to all active subscriptions. If the event requires specialized filtering, the agent runs `bulk_create_filters` to ensure only the correct targets receive the notification. The entire process runs autonomously based on the crew's shared memory and goals.

Setup guide

Set up Convoy MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Convoy tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Convoy Analyst",
    goal="Access and analyze Convoy data via MCP.",
    backstory="Expert analyst with direct Convoy access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Convoy transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Convoy Analyst",
        goal="Access and analyze Convoy data via MCP.",
        backstory="Expert analyst with direct Convoy access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Convoy transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

The easiest way is passing the Vinkius HTTP URL directly into the agent's `mcps` array. For finer control, import `MCPServerHTTP` from `crewai.mcp` and use a `tool_filter` to limit which agents can run tools like `delete_endpoint`.

Yes. Because CrewAI agents share memory and context, they can access the same Vinkius endpoint. One agent can find a broken subscription via `list_subscriptions` while another uses `activate_endpoint` to resolve the blocker.

If your crew triggers too many calls to `fanout_event` or `create_event`, the Convoy API may return rate limit headers. You must handle these 429 responses in your CrewAI task definitions to prevent the agents from looping.

CrewAI supports stdio, SSE, and Streamable HTTP transports. The Vinkius hosted MCP server operates over secure HTTP/SSE, allowing your Python-based crew to invoke tools instantly from any environment.

Yes. Your API keys are injected directly into the Vinkius zero-trust sandbox environment. CrewAI agents only see the high-level tool definitions like `create_source` and never have direct access to the underlying credentials.

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