How to Use the Marketo MCP in AutoGen

Q: How do I configure Marketo tools for an AutoGen assistant?

Install the autogen-extmcp package. Use mcpservertools with a StreamableHttpServerParams configuration, then pass the resulting list directly into your AssistantAgent.

Q: Can multiple AutoGen agents use the Marketo MCP Server simultaneously?

Yes. The McpToolAdapter automatically converts the schemas. Any agent in your conversation group that has the tools injected can call getcampaignbyid when needed.

Give your AutoGen agents access to the Marketo MCP Server to debate lead routing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marketo MCP to AutoGen

Create your Vinkius account to connect Marketo 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 Marketo with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate lead quality with AutoGen agents

Lead scoring is subjective. You can spin up an AutoGen system where a Sales Agent and a Marketing Agent debate the readiness of a prospect. They pull the raw facts by calling `get_lead_by_email` and review the data together. The Marketing Agent might pull the prospect's recent behavior using `list_activities` to argue for a sales handoff. The Sales Agent reviews the same activity log and pushes back, demanding more engagement before accepting the lead. They negotiate until they reach a consensus.

Audit the Marketo MCP Server programs

Marketing instances turn into a mess over time. You can assign a Compliance Agent to review your current setup. It runs `list_programs` to grab everything currently active and checks for naming convention violations. If it spots an anomaly, it digs deeper by calling `get_program_by_id`. A separate Operations Agent reviews the findings and proposes a cleanup plan. They work through the entire instance autonomously.

Negotiate campaign targeting

Building an audience requires balancing volume and precision. Your agents can analyze your current segments by pulling `list_static_lists` and reviewing the member counts. They discuss whether the list is too broad. To get specific, one agent calls `list_leads_by_list` to sample the actual prospects. Another agent reviews the active campaigns via `list_smart_campaigns` to ensure these leads aren't already receiving conflicting messages.

Setup guide

Set up Marketo 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 Marketo 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="Marketo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration, then pass the resulting list directly into your `AssistantAgent`.

Yes. The `McpToolAdapter` automatically converts the schemas. Any agent in your conversation group that has the tools injected can call `get_campaign_by_id` when needed.

Scripts execute rigid logic. AutoGen allows agents to handle ambiguity. If `list_activities` returns unusual patterns, the agents can discuss the anomaly instead of just failing.

You should configure a Manager Agent to monitor tool usage. If the system spams `get_lead_by_id`, the manager can instruct the group to pause or batch their requests.

The Vinkius infrastructure relies on stateless execution. When your agents debate a specific prospect and call `get_lead_by_email`, the token auth happens in an isolated sandbox, meaning no customer records persist on our servers after the HTTP response clears.

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