How to Use the DISQO MCP in AutoGen

Q: How do AutoGen agents coordinate when calling DISQO tools?

Register tools like listrunningresearchprojects with the assistant agent, allowing it to fetch live project lists. The agent then shares this data in the group chat, where other agents can analyze the project health.

Q: Can I use the DISQO MCP Server to automate research panel selection in AutoGen?

Your planner agent can query listlargestresearchpanels to find the most viable audience segments. It then presents these options to the execution agent, which selects the optimal panel based on current project constraints.

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

Use the autogen-extmcp package to connect to your Vinkius endpoint via the streamable HTTP transport. The adapter automatically maps the ten DISQO tools to the schema format that AutoGen agents expect.

Q: How do AutoGen agents resolve conflicting data from DISQO?

When quickbehavioralaudit and listbehavioralmetrics return differing levels of detail, the agents debate the discrepancies. The analyst agent will request a deeper dive, while the budget agent monitors token usage.

Q: How is the privacy of DISQO research projects maintained in AutoGen?

All tool calls to listinsightprojects go through the zero-trust Vinkius sandbox, ensuring your API credentials remain hidden. The raw project configurations and audience metrics are only shared within your local AutoGen session, preventing external data leaks.

Let AutoGen agents debate consumer research strategies using live behavioral metrics from the DISQO 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 DISQO MCP to AutoGen

Create your Vinkius account to connect DISQO 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 DISQO with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate on DISQO audience targeting

`list_research_audiences` provides the raw audience segment definitions that your AutoGen research agent uses to draft targeting proposals. A separate analyst agent then reviews these proposals, evaluating whether the selected segments match the campaign goals. This collaborative loop ensures that targeting decisions are thoroughly vetted before any budget is spent. The agents negotiate back and forth, refining the audience parameters until they reach a consensus based on actual panel availability.

Automated behavioral audits via AutoGen

`quick_behavioral_audit` gives your AutoGen performance agent a rapid snapshot of active consumer behaviors. The agent analyzes these high-level metrics and flags sudden shifts in user activity to the rest of the agent group. If a shift is detected, a secondary agent is triggered to investigate the underlying causes. By dividing the labor, your agent team monitors behavioral trends continuously without hitting API limits.

Verifying project health using DISQO MCP Server tools

`get_project_details` allows an AutoGen auditor agent to check the exact status and configuration of running studies. The auditor agent compares these details against the project plan and flags any discrepancies to the coordinator agent. This automated oversight keeps your research projects on track without human monitoring. The agents handle the tracking, verification, and reporting, only alerting you when a project requires human intervention.

Setup guide

Set up DISQO 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 DISQO 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="DISQO_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Register tools like `list_running_research_projects` with the assistant agent, allowing it to fetch live project lists. The agent then shares this data in the group chat, where other agents can analyze the project health.

Your planner agent can query `list_largest_research_panels` to find the most viable audience segments. It then presents these options to the execution agent, which selects the optimal panel based on current project constraints.

Use the `autogen-ext[mcp]` package to connect to your Vinkius endpoint via the streamable HTTP transport. The adapter automatically maps the ten DISQO tools to the schema format that AutoGen agents expect.

When `quick_behavioral_audit` and `list_behavioral_metrics` return differing levels of detail, the agents debate the discrepancies. The analyst agent will request a deeper dive, while the budget agent monitors token usage.

All tool calls to `list_insight_projects` go through the zero-trust Vinkius sandbox, ensuring your API credentials remain hidden. The raw project configurations and audience metrics are only shared within your local AutoGen session, preventing external data leaks.

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