How to Use the AskNicely MCP in AutoGen

Q: How do AutoGen agents connect to AskNicely?

Install autogen-extmcp and configure the StreamableHttpServerParams with your Vinkius URL. Pass the tools directly into your AssistantAgent setup.

Give your AutoGen multi-agent squads direct access to AskNicely customer sentiment and survey tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AskNicely MCP to AutoGen

Create your Vinkius account to connect AskNicely 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 AskNicely with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AskNicely MCP Server for AutoGen

Single agents miss the big picture. AutoGen lets you build a customer success squad where different personas debate the meaning of your NPS data. One agent runs `get_statistics` to fetch the raw scores and claims everything is fine. A second agent plays devil's advocate. It calls `list_responses` to read the actual text feedback, finding hidden complaints. They argue over the discrepancy until they reach a consensus on customer health.

Negotiate Survey Triggers

Sending surveys blindly annoys users. In a multi-agent setup, a marketing agent might propose sending a blast, but a rate-limit agent pushes back. They review the current audience using the `list_contacts` tool. Once they agree on the target list, the execution agent takes over. It invokes `trigger_survey` to add the approved contacts and send the NPS requests. The decision requires deliberation, not just a simple script.

Maintain Connection Health

Complex agent conversations break if the underlying API fails. Your operations agent can periodically test the integration by calling `get_account_check`. This ensures the AskNicely endpoint is actually listening. Catching auth errors early saves expensive LLM tokens. If the check fails, the agents pause their debate and alert a human operator. The system heals itself before attempting to pull more responses.

Setup guide

Set up AskNicely 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 AskNicely 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="AskNicely_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp] and configure the StreamableHttpServerParams with your Vinkius URL. Pass the tools directly into your AssistantAgent setup.

Yes. You assign specific tools to different personas. The analyst agent gets get_statistics, while the outreach agent gets trigger_survey.

The McpToolAdapter automatically converts the tool schemas. Your agents read the descriptions for list_responses and decide when to use it during their debate.

Only if you allow it. You can require human-in-the-loop approval before any agent is allowed to execute trigger_survey.

Vinkius manages the connection using a zero-trust V8 sandbox. When your agents debate the text pulled from list_responses, the raw data remains strictly between AskNicely and your local environment.

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