How to Use the Cometly MCP in AutoGen

Q: How do AutoGen agents share Cometly tool outputs during a conversation?

When one agent calls getcampaignstats, the output is posted directly into the group chat context. Other agents in the conversation can immediately read those metrics to debate campaign performance.

Q: Can I restrict which AutoGen agent has permission to call Cometly tracking tools?

Yes. You can register writing tools like trackpurchase or tracklead exclusively to your tracking agent, while leaving read-only tools like listcampaigns accessible to your analyst agent.

Q: How do I register the Cometly MCP Server tools with AutoGen?

Use mcpservertools with your Vinkius HTTP server parameters to fetch the tools. Pass the resulting list directly to your AssistantAgent constructor to give them tracking capabilities.

Q: How do AutoGen agents handle errors if a conversion event fails to track?

If trackevent returns an error, your executing agent reports the failure to the group chat. A supervisor agent can then analyze the payload and instruct the tracking agent to retry with corrected contact data.

Q: Is my Cometly customer journey data secure during AutoGen conversations?

Yes. All calls to listcontacts and listevents run inside an ephemeral V8 sandbox managed by Vinkius. Your sensitive marketing data and ad credentials are never stored or exposed to external networks outside your local MCP client environment.

Deploy AutoGen marketing agents that debate campaign performance and coordinate Cometly event tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cometly MCP to AutoGen

Create your Vinkius account to connect Cometly 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 Cometly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate your Cometly campaign performance

Querying `get_campaign_stats` and `list_campaigns` gives your AutoGen agents the raw data they need to debate ad performance. Set up a multi-agent workflow where an analyst agent queries the metrics and a finance agent challenges the ad spend. By using this MCP Server, your AutoGen agents negotiate based on real-time data instead of static reports. They reach a consensus on performance trends before flagging any issues to your marketing team.

Coordinate conversion tracking across specialized AutoGen agents

Calling `track_lead` or `track_purchase` allows your tracking agent to register events in Cometly once the group reaches consensus. This multi-agent coordination prevents duplicate events. The AutoGen agents verify with each other that the contact journey returned by `list_contacts` doesn't already contain the conversion before firing a new `track_event` call.

Audit ad account access using an MCP Server

Running `list_ad_accounts` allows your security agent to audit connected Meta or Google integrations. Deploy a security agent that regularly checks your connected platforms inside your AutoGen group. If the agent detects an unrecognized account or a sudden drop in tracked events via `list_events`, it alerts your admin agent to pause operations, ensuring your marketing spend remains fully audited.

Setup guide

Set up Cometly 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 Cometly 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="Cometly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cometly 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="Cometly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cometly 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 Cometly. 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 Cometly 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 Cometly MCP in AutoGen

When one agent calls `get_campaign_stats`, the output is posted directly into the group chat context. Other agents in the conversation can immediately read those metrics to debate campaign performance.

Yes. You can register writing tools like `track_purchase` or `track_lead` exclusively to your tracking agent, while leaving read-only tools like `list_campaigns` accessible to your analyst agent.

Use `mcp_server_tools` with your Vinkius HTTP server parameters to fetch the tools. Pass the resulting list directly to your `AssistantAgent` constructor to give them tracking capabilities.

If `track_event` returns an error, your executing agent reports the failure to the group chat. A supervisor agent can then analyze the payload and instruct the tracking agent to retry with corrected contact data.

Yes. All calls to `list_contacts` and `list_events` run inside an ephemeral V8 sandbox managed by Vinkius. Your sensitive marketing data and ad credentials are never stored or exposed to external networks outside your local MCP client environment.

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