How to Use the Chili Piper MCP in AutoGen

Q: How do I load Chili Piper tools into AutoGen?

Install the autogen-extmcp package. Call mcpservertools with your Vinkius Streamable HTTP URL and pass the resulting tools to your AssistantAgent.

Q: Can AutoGen agents read my Chili Piper routing rules?

They can call listroutes and getroutedetails. Multiple agents can then review your top-level concierge rules and debate if they need adjusting.

Let your AutoGen agents debate and negotiate Chili Piper routing rules and queue distributions autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chili Piper MCP to AutoGen

Create your Vinkius account to connect Chili Piper 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 Chili Piper with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen MCP Server consensus routing

Round-robin distribution often ignores context. You can set up one agent to evaluate lead quality while another checks rep capacity using `get_availability` through the AutoGen MCP Server. They debate the best assignment. Once they reach consensus, a third agent executes `generate_booking_link` to lock in the meeting. The system handles complex routing logic through conversation rather than static rules.

Queue optimization and rebalancing

Sales velocity drops when queues get unbalanced. Your performance agent pulls weight distributions using `get_queue_details` and native groupings with `list_queues`. A manager agent reviews these metrics and argues for shifting reps around. They use `list_members` to verify active accounts before finalizing a new distribution strategy.

Automated schedule auditing

Dead meetings clog up the calendar. An auditor agent runs `list_meetings` to find old scheduling blocks that never converted. It flags these to a compliance agent. If they agree the meeting is dead, they trigger `cancel_meeting` to irreversibly vaporize the hold and free up the rep's time.

Setup guide

Set up Chili Piper 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 Chili Piper 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="Chili Piper_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the autogen-ext[mcp] package. Call mcp_server_tools with your Vinkius Streamable HTTP URL and pass the resulting tools to your AssistantAgent.

They can call list_routes and get_route_details. Multiple agents can then review your top-level concierge rules and debate if they need adjusting.

That is exactly how it works. A calendar agent checks white-space while a priority agent argues for an earlier slot. They settle on a time and call the MCP Server to book it.

The McpToolAdapter handles it automatically. Your agents see native Python function signatures for get_meeting_details without you writing boilerplate.

Every connection requires just one endpoint token. When agents pull explicit member accounts or queue structures, Vinkius processes the request in an isolated, temporary environment that leaves zero residual footprint.

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