How to Use the Callpicker MCP in AutoGen

Q: Can AutoGen agents use Callpicker to make calls?

Yes. One agent can propose using the makecall tool, and other agents can debate the purpose or timing before the call is actually initiated. This consensus-driven approach prevents accidental or unauthorized actions.

Q: Callpicker and AutoGen for lead follow-up strategy?

Exactly. One agent pulls lead data with getcalldetails. Another agent analyzes the lead's source. A third agent proposes a follow-up action. They agree on a plan before one of them is authorized to execute a tool like makecall.

Let your AutoGen agents debate how to handle phone leads. They'll analyze call data, check system status, and agree on a plan.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Callpicker MCP to AutoGen

Create your Vinkius account to connect Callpicker 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 Callpicker with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Call Analysis Team

Create an AutoGen team to analyze marketing performance. One agent, the 'Analyst,' can use `get_cdr_report` to get a high-level view of call volume and present its findings to the group. A second agent, the 'Investigator,' can then challenge those findings. It might use `list_call_logs` to find specific anomalies in the data and then `get_call_details` to check the marketing source for a low-performing number. They debate until they converge on which campaigns are actually working.

Debate System Operations Safely

Have your agents manage the phone system. A 'Monitor' agent can periodically use `get_pbx_system_status` and report back to the group. If it finds a problem, it starts a conversation. A 'Responder' agent could then propose a solution, like running a test call with `make_call`. But a 'Security' agent might first insist on checking available lines with `list_pbx_extensions` to avoid crossing channels. The agents converse to find the safest course of action, which is the whole point of using this MCP Server with AutoGen.

Manage Recordings by Consensus

Assign agents specific roles for handling recordings. A 'Compliance' agent can use `list_call_recordings` to check for recordings that need to be archived or deleted based on your company's data retention policy. When a user asks for a specific recording, a 'Support' agent can find it and propose fetching the file with `get_recording_url`. The Compliance agent can then verify the request is legitimate before allowing the action. The conversation log provides a full audit trail of their decision-making process.

Setup guide

Set up Callpicker 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 Callpicker 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="Callpicker_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You provide the list of Callpicker tools to your agents. Any agent in the conversation can then invoke a tool, like `get_call_details`, to gather facts, support its arguments, or perform a task that the group agrees on.

Yes. One agent can propose using the `make_call` tool, and other agents can debate the purpose or timing before the call is actually initiated. This consensus-driven approach prevents accidental or unauthorized actions.

Exactly. One agent pulls lead data with `get_call_details`. Another agent analyzes the lead's source. A third agent proposes a follow-up action. They agree on a plan before one of them is authorized to execute a tool like `make_call`.

The MCP Server provides a standardized, secure way to expose tools to your agents. Vinkius handles the authentication, sandboxing, and boilerplate code so you can focus on designing the agent conversation logic.

The server processes call metadata from your PBX system — this includes call logs, extension lists, and recording links. This data is streamed directly to your AutoGen agents for use in their conversation; it is not stored or analyzed by the Vinkius platform. All connections are ephemeral and secure.

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