How to Use the Landing MCP in AutoGen

Q: How do I register Landing tools with AutoGen?

Install autogen-extmcp. Use mcpservertools with your server URL, then pass the returned list to your AssistantAgent constructor. The adapter handles the schema translation.

Q: How do I stop an AutoGen agent from deleting a Landing webhook?

Do not include deletelandingwebhook in the tool list for that specific agent. Give destructive tools only to a highly constrained executor agent that requires human-in-the-loop approval.

Q: Why does my debate loop infinitely on projects?

If agents disagree on the interpretation of listlandingprojects, they might argue forever. Set a strict maxconsecutiveautoreply limit on your agents to force termination.

Q: Who sees the PII pulled from my campaigns?

The listlandingleads tool fetches real customer names and emails. Vinkius processes this through a strict, zero-trust V8 isolate. The data only exists in memory during the MCP Server execution and your local chat history.

Let your AI agents debate marketing strategy. Connect AutoGen to this MCP Server and build consensus-driven campaign automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Landing MCP to AutoGen

Create your Vinkius account to connect Landing 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 Landing with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent Landing control in AutoGen

One agent making decisions about your Landing campaigns is risky. AutoGen lets you build a team of agents that argue before they act. You give a marketing agent access to the Landing MCP Server to propose campaign changes based on `list_landing_pages`. A separate analytics agent reviews that proposal. It pulls conversion data via `list_landing_leads`, challenges the marketing agent's logic, and forces a revision. They negotiate the best path forward before executing any changes.

Require consensus for webhooks

Landing infrastructure changes need oversight. When an agent wants to route traffic, it proposes running `create_landing_webhook`. Instead of firing immediately, a security agent intercepts the request to verify the destination URL. The same applies to teardowns. If a cleanup agent suggests firing `delete_landing_webhook`, a project manager agent checks `list_landing_projects` to ensure the campaign is actually finished. You get automated safety checks built into the conversation flow.

Cross-examine campaign setups

You can build a diagnostic chat where agents interrogate your Landing account configuration. An auditor agent calls `get_my_landing_profile` to verify permissions, then pulls `list_landing_webhooks` to map out your data flow. If it finds a broken route, it alerts a fixer agent. The agents discuss the discrepancy, agree on a fix, and implement it. You just watch the terminal output while they solve the problem.

Setup guide

Set up Landing 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 Landing 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="Landing_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with your server URL, then pass the returned list to your AssistantAgent constructor. The adapter handles the schema translation.

Yes. You can provide the same tool list to different agents in your conversation. Both your planner and executor agents can share the MCP Server to verify state.

Do not include `delete_landing_webhook` in the tool list for that specific agent. Give destructive tools only to a highly constrained executor agent that requires human-in-the-loop approval.

If agents disagree on the interpretation of `list_landing_projects`, they might argue forever. Set a strict `max_consecutive_auto_reply` limit on your agents to force termination.

The `list_landing_leads` tool fetches real customer names and emails. Vinkius processes this through a strict, zero-trust V8 isolate. The data only exists in memory during the MCP Server execution and your local chat history.

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