How to Use the Thoughtly MCP in AutoGen

Q: How do I configure Thoughtly for AutoGen?

Install autogen-extmcp. Pass your endpoint URL into StreamableHttpServerParams, extract the tools, and hand them directly to your AssistantAgent constructor.

Q: How does AutoGen update a Thoughtly record?

An agent fetches the current details with getcontact, determines what changed, and applies the new information via updatecontact.

Q: Can AutoGen review my Thoughtly voice agent setups?

Your configuration agent can pull the active list using listinterviews and inspect specific parameters via getinterview to ensure your bots are using the right scripts.

Give your AutoGen agents a phone. Let your conversational AI team debate, decide, and dial out using Thoughtly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Thoughtly MCP to AutoGen

Create your Vinkius account to connect Thoughtly to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Thoughtly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Call Execution

AutoGen shines when agents collaborate. By adding this MCP Server, you can assign a research agent to evaluate leads while an execution agent holds the phone. Once they agree a prospect is worth contacting, the execution agent fires `trigger_call`. After the dial finishes, an analyst agent can step in. It runs `list_calls` to verify the system logged the outbound attempt correctly, ensuring your team has a clear audit trail of who contacted whom.

Thoughtly MCP Server Data Retrieval

Your agents need facts to debate effectively. If a previous conversation went poorly, a QA agent can pull the exact transcript using `get_call_history`. The team reviews the text to figure out why the prospect hung up. Before initiating a new campaign, a manager agent might need to check your current account limits. It calls `get_user` to verify your profile status and available credits, preventing failed dials.

Debating CRM Operations

Managing a messy database requires careful deliberation. A data-cleaning agent can pull your entire address book via `list_contacts` and present duplicates to a supervisor agent for review. They negotiate which records to keep based on your custom rules. Once they reach a consensus, the execution agent permanently removes the redundant entry using `delete_contact`. No human intervention required.

Setup guide

Set up Thoughtly 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 Thoughtly 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="Thoughtly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp]. Pass your endpoint URL into StreamableHttpServerParams, extract the tools, and hand them directly to your AssistantAgent constructor.

Yes. If a web-scraping agent finds a new lead, it can hand the data to an admin agent that executes `create_contact` to log it in your system.

An agent fetches the current details with `get_contact`, determines what changed, and applies the new information via `update_contact`.

Your configuration agent can pull the active list using `list_interviews` and inspect specific parameters via `get_interview` to ensure your bots are using the right scripts.

Raw conversation audio and text logs flow securely from the telephony provider to your local machine. Vinkius routes this traffic through isolated, stateless containers that destroy themselves after the request completes, leaving zero trace of your 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