How to Use the CommPeak MCP in AutoGen

Q: How do AutoGen agents coordinate when using CommPeak?

One agent runs listleads to find prospects, while another analyzes the data and calls sendsms once they reach a consensus.

Q: Can I restrict which AutoGen agent can call CommPeak write tools?

Yes. You register tools like deletelead only to your administrator agent, while leaving read tools open to your analyst agents.

Q: Can agents execute multiple CommPeak tools in a single turn?

Yes, an agent can call getleaddetails and getcampaigndetails in one turn to gather all necessary context over the MCP link before making a decision.

Deploy AutoGen agents that debate sales strategies and execute lead management via CommPeak.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CommPeak MCP to AutoGen

Create your Vinkius account to connect CommPeak 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 CommPeak with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent lead qualification with CommPeak MCP Server

The `create_lead` tool lets your qualification agent insert vetted prospects into active campaigns. A researcher agent finds the lead, a scoring agent validates the fit, and the execution agent calls this tool to push them to the dialer. If a lead is deemed unqualified during the debate, the `delete_lead` tool is invoked to remove them. This multi-agent verification prevents bad numbers from entering your outbound call queues.

Collaborative SMS campaign execution in AutoGen

The `send_sms` tool lets your messaging agent initiate contact with leads. Before sending, a compliance agent reviews the text payload to ensure it matches your company's guidelines. Once sent, another agent monitors delivery using `get_sms_status` and `list_recent_sms`. If a message fails, the agents discuss whether to retry or flag the number for manual review.

Autonomous campaign optimization

The `get_campaign_details` tool provides active dialer metrics to your analyst agent. The analyst reviews these numbers and coordinates with the operations agent to shift resources between different campaigns. Using `list_dialer_campaigns` and `list_leads`, your agents build a complete picture of your calling operations. They dynamically reallocate leads based on which campaigns show the highest conversion rates.

Setup guide

Set up CommPeak 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 CommPeak 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="CommPeak_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent runs `list_leads` to find prospects, while another analyzes the data and calls `send_sms` once they reach a consensus.

Yes. You register tools like `delete_lead` only to your administrator agent, while leaving read tools open to your analyst agents.

The MCP tool adapter automatically translates the JSON schemas of tools like `create_lead` into the format AutoGen expects.

Yes, an agent can call `get_lead_details` and `get_campaign_details` in one turn to gather all necessary context over the MCP link before making a decision.

Your campaign IDs and SMS text payloads are transmitted over secure, ephemeral MCP sandboxes. No persistent logs of your message content are kept on our infrastructure.

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