How to Use the Amplemarket MCP in AutoGen

Q: How can I make two AutoGen agents work together on my Amplemarket account?

Assign the Amplemarket tools to one agent, like an AssistantAgent. Then create another agent, like a UserProxyAgent, that gives it tasks. The agents will converse to decide which tools, like searchpeople or addleadstosequence, to use to complete the task.

Q: Can I have one AutoGen agent find leads in Amplemarket and another approve them?

Yes, that's a perfect use case. The first agent uses searchpeople and presents the results. The second agent, which could even be you via a UserProxyAgent, reviews the list and gives the go-ahead before a third agent calls addleadstolist.

Q: What's a good multi-agent setup for managing Amplemarket sequences with AutoGen?

Try a three-agent setup. A 'Researcher' uses listsequences to see what's available. A 'Strategist' decides which sequence fits a new lead. An 'Executor' makes the final call to addleadstosequence.

Assemble a team of AutoGen agents to debate and execute your Amplemarket sales strategy. Go from idea to outreach, automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplemarket MCP to AutoGen

Create your Vinkius account to connect Amplemarket 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 Amplemarket with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Your Prospecting Strategy

Create a team of specialized agents. One agent, the 'Prospector', uses `search_people` to find potential leads. Another agent, the 'Qualifier', reviews those leads and decides if they're a good fit for the business. The Prospector presents its findings. The Qualifier can push back: 'This contact's title isn't senior enough. Find me VPs using `find_person` instead.' They converse until they reach a consensus on a high-quality lead list, which is then created with `create_lead_list`.

Consensus-Driven Sequence Assignment with AutoGen

Build on your agent team. A 'SequenceManager' agent uses `list_sequences` to know all available outreach campaigns. A 'Strategist' agent holds the high-level goals for the quarter. After the Qualifier approves a lead, the Strategist and SequenceManager debate the best next step. 'This is a CEO, put them in the exec outreach sequence,' one might say. The other confirms the sequence exists and then an 'Executor' agent makes the call to `add_leads_to_sequence`. It's a team decision, not a single command.

A Reactive, Multi-Agent Sales Team

You can have an 'Analyst' agent that periodically calls `list_lead_lists` to monitor list growth. If a list is stagnant, it can start a conversation with the Prospector agent to get more leads. An 'Operator' agent can listen for external events. When a new high-value company is funded, the Operator can use `trigger_custom_signal` in Amplemarket and tell the other agents, 'New priority target, find me the CTO.' This creates a reactive system that manages your sales pipeline through conversation.

Setup guide

Set up Amplemarket 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 Amplemarket 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="Amplemarket_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Assign the Amplemarket tools to one agent, like an `AssistantAgent`. Then create another agent, like a `UserProxyAgent`, that gives it tasks. The agents will converse to decide which tools, like `search_people` or `add_leads_to_sequence`, to use to complete the task.

Yes, that's a perfect use case. The first agent uses `search_people` and presents the results. The second agent, which could even be you via a `UserProxyAgent`, reviews the list and gives the go-ahead before a third agent calls `add_leads_to_list`.

Try a three-agent setup. A 'Researcher' uses `list_sequences` to see what's available. A 'Strategist' decides which sequence fits a new lead. An 'Executor' makes the final call to `add_leads_to_sequence`.

They can. Once your agents agree on a set of new contacts, one of them can be tasked with calling the `create_lead_list` tool. This is a common final step after a prospecting and qualification debate.

Your Amplemarket contact and sequence information is only processed within the Vinkius sandbox for the instant your agent calls a tool. The data is sent to Amplemarket's API and the result is returned to your AutoGen agents. Vinkius does not log or store any of this private lead data.

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