How to Use the Agency Elephant MCP in AutoGen

Q: How do I set up an AutoGen AssistantAgent to use the Agency Elephant tools?

After installing autogen-extmcp, you use the mcpservertools function with your server URL. This returns a list of tools that you pass directly into the tools parameter of your AssistantAgent's constructor.

Q: How does the McpToolAdapter in AutoGen handle the schemas for the Agency Elephant MCP server tools?

It handles it for you. The mcpservertools function fetches the tool specifications from the MCP Server and automatically converts them into a format that AutoGen agents can understand and execute. You don't have to do any manual mapping.

Build multi-agent teams in AutoGen that debate and execute the best way to manage your Agency Elephant leads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agency Elephant MCP to AutoGen

Create your Vinkius account to connect Agency Elephant 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 Agency Elephant with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Lead Strategy

This server gives you the tools to build a team of specialized agents. A 'Prospector' agent can use `create_lead` to add a new person. A 'Strategist' agent can then inspect the lead with `get_lead_details`, check available campaigns with `list_campaigns`, and propose a plan. This is AutoGen's conversational power. The agents don't just execute a script; they discuss the plan in a group chat. You can see them reason about the best way to handle a new lead, with one agent executing the `trigger_drip_campaign` tool only after they all agree.

An MCP Server for Multi-Agent Audits

Set up an 'Auditor' agent to periodically run `list_leads` and find prospects that have gone cold. When it finds one, it presents the lead's ID to a 'Closer' agent in the group chat. In AutoGen, this creates a system of checks and balances. The Closer agent can use `get_lead_details` to verify the Auditor's findings before deciding what to do next. Maybe it uses `add_lead_to_group` to move the lead to a 'needs-follow-up' list. The action only happens after a conversation.

Launch Campaigns with Agent Consensus

One agent can propose starting a campaign for a high-value lead using `trigger_drip_campaign`. But a 'Compliance' agent in the same chat can first check if that lead is already active in another campaign, preventing duplicate messages. This is where AutoGen really works. The agents debate the action. 'Is this lead in the right group?' 'Did we get their consent for this campaign?' They use the Agency Elephant tools to pull evidence and present their arguments before coming to a decision. You're building a system that thinks, and argues, before it acts.

Setup guide

Set up Agency Elephant 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 Agency Elephant 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="Agency Elephant_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

After installing `autogen-ext[mcp]`, you use the `mcp_server_tools` function with your server URL. This returns a list of tools that you pass directly into the `tools` parameter of your AssistantAgent's constructor.

Yes, that's a perfect use case for AutoGen. The first agent calls `create_lead` and posts the result to the group chat. The second agent sees the new `lead_id` and then calls `trigger_drip_campaign`.

An agent might propose an action, like 'Add lead 123 to campaign XYZ.' Another agent could reply, 'Wait, my check with `get_lead_details` shows lead 123 is already in a campaign. We should not proceed.' They go back and forth until they agree on a safe action.

It handles it for you. The `mcp_server_tools` function fetches the tool specifications from the MCP Server and automatically converts them into a format that AutoGen agents can understand and execute. You don't have to do any manual mapping.

The agents will exchange lead details, campaign names, and user info in their conversation. This all happens within the Vinkius zero-trust sandbox. Each session is fully isolated, and no data from the conversation or API calls persists after your run is complete.

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