How to Use the Delighted MCP in AutoGen

Q: How do I register the Delighted MCP Server with AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. Pass the resulting tool list directly to your AssistantAgent constructor to give them access.

Q: Can AutoGen agents collaborate on analyzing Delighted feedback?

Yes, one agent can fetch data using listsurveyresponses and share the raw JSON with other agents in the group chat. The team can then debate the feedback and decide on the next steps.

Q: How do AutoGen agents handle tool execution errors?

If a tool call like getpersonfeedbackhistory fails due to an invalid email, the agent receives the error. The conversation loop allows the agent to correct the input and try again.

Let your AutoGen agents debate and act on customer feedback and NPS trends using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Delighted MCP to AutoGen

Create your Vinkius account to connect Delighted 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 Delighted with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve customer issues using this MCP Server

By calling `list_recent_detractors`, your retriever agent can find unhappy customers and pull their raw feedback. Once identified, a support agent analyzes the context, allowing them to discuss the issue, negotiate the best approach, and agree on how to handle the account. This consensus-driven model ensures higher quality responses. The agents use `get_response_details` to pull the exact feedback and debate the customer's intent before taking any action.

Automate survey triggers via consensus

Your agents can invoke `add_person_to_survey` to schedule a survey invite once they reach a consensus. Once a performance agent and a customer success agent agree that a user's onboarding is complete, they trigger the tool to schedule the invite. The MCP Server handles the connection directly. AutoGen's McpToolAdapter converts the schemas automatically, so your agents can call the tool during their conversation without manual formatting.

Track sentiment trends using specialized agents

Your promoter agent can call `list_top_promoters` to find your biggest fans and track sentiment trends. Meanwhile, the detractor agent uses `get_nps_metrics_summary` to track overall satisfaction, and they compare notes to give you a balanced view of your product health. They can even search for specific issues using `search_responses_by_comment`. By analyzing these keywords, the agents can coordinate to find out if a recent release caused a sudden spike in negative feedback.

Setup guide

Set up Delighted 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 Delighted 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="Delighted_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp] and use mcp_server_tools with your Vinkius HTTP URL. Pass the resulting tool list directly to your AssistantAgent constructor to give them access.

Yes, one agent can fetch data using list_survey_responses and share the raw JSON with other agents in the group chat. The team can then debate the feedback and decide on the next steps.

Yes, the adapter supports both transport protocols. On Vinkius, you will typically use the Streamable HTTP transport to connect your agents to the hosted server securely.

If a tool call like get_person_feedback_history fails due to an invalid email, the agent receives the error. The conversation loop allows the agent to correct the input and try again.

The MCP Server runs in an isolated V8 sandbox. This means your customer contact details and NPS scores are never written to disk or exposed to external networks outside of the direct API connection.

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