How to Use the Keap MCP in AutoGen

Q: How do I register Keap tools in AutoGen?

Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius URL. Pass the returned list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents share the same Keap connection?

Yes. McpToolAdapter converts the schemas automatically. You give the tools to whichever specific agents need CRM access during the debate.

Q: How do AutoGen agents handle Keap API errors?

If a tool like getcontact fails, the error feeds back into the chat. The agents discuss the failure and attempt a different search strategy.

Q: Is my sales pipeline data secure during agent debates?

Deal values and closing stages pulled from listopportunities stay within your controlled environment. Vinkius manages the authentication via a secure, stateless tunnel that drops the connection immediately after the tool call resolves.

Build AutoGen agent teams that debate and execute Keap MCP Server workflows autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keap MCP to AutoGen

Create your Vinkius account to connect Keap 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 Keap with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent campaign deliberation

AutoGen exposes `list_campaigns` and `list_tags` to a group of specialized agents. A marketing agent proposes a new tag structure, while a compliance agent reviews it for privacy violations. They negotiate the final approach before taking action. Once they reach consensus, an execution agent steps in and calls `apply_tag_to_contact` to make the agreed-upon changes in your CRM.

Debate routing rules with AutoGen

Your system pulls raw lead data using `list_contacts` and `get_contact`. A sales agent argues for immediate outreach, while a qualification agent pushes to wait for more signals. The agents review historical win rates using `list_opportunities`. After analyzing the facts, they decide whether to push the lead to a rep or drop them into a nurture sequence.

Reconcile records autonomously

The Keap MCP server feeds `list_invoices` and `list_orders` into your conversational framework. An audit agent cross-checks these records against `get_business_profile` to ensure billing details match. If an agent spots a discrepancy, it flags the issue in the chat. A separate resolution agent can then use `create_contact` to build a profile for a missing billing admin.

Setup guide

Set up Keap 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 Keap 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="Keap_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius URL. Pass the returned list directly into your `AssistantAgent` constructor.

Yes. `McpToolAdapter` converts the schemas automatically. You give the tools to whichever specific agents need CRM access during the debate.

If a tool like `get_contact` fails, the error feeds back into the chat. The agents discuss the failure and attempt a different search strategy.

The MCP protocol handles that. The server advertises the required inputs for operations like `list_users`, and the adapter translates them for the LLM.

Deal values and closing stages pulled from `list_opportunities` stay within your controlled environment. Vinkius manages the authentication via a secure, stateless tunnel that drops the connection immediately after the tool call resolves.

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