How to Use the Tactiq MCP in AutoGen

Q: What is the best way to use AutoGen with transcript data?

Give it both gettranscript and searchtranscripts. You can have one agent search for keywords, and a second agent analyze the retrieved context against known company policies, leading to a highly vetted conclusion.

Q: How do I check initial API connectivity with AutoGen and Tactiq?

The first step is letting an agent run checktactiqstatus. This provides immediate, verifiable proof that all MCP tools are connected and ready to be used in the subsequent debates.

Facilitate consensus decisions with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Tactiq MCP to AutoGen

Create your Vinkius account to connect Tactiq 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 Tactiq with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Simulate agent debate over meeting outcomes.

AutoGen is perfect when the answer isn't obvious. You can set up multiple agents—say, a 'Risk Analyst' and an 'Efficiency Manager'—to discuss the results of `get_summary`. They challenge each other's initial conclusions on the optimal next steps. The resulting conversation simulates consensus-driven decision making. Instead of one summary, you get a negotiated outcome that addresses competing perspectives based on the raw meeting data.

Process multiple viewpoints simultaneously.

Need to know who said what? Give your agents access to both `list_speakers` and `get_transcript`. One agent might focus purely on speaker attribution, while another focuses on the content. They debate which points are most important based on who raised them. This process is ideal for complex project reviews where multiple stakeholders have conflicting priorities or varying levels of involvement.

Develop structured conversation flows.

The framework allows you to pass the MCP tool list directly to an agent constructor. The agents then use their internal logic to decide when and how to call tools like `get_action_items` or `list_meetings`. They treat the data retrieval itself as a part of the discussion. This turns simple API calls into conversational steps, making your system feel much more natural.

Setup guide

Set up Tactiq 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 Tactiq 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="Tactiq_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Set up agents with different roles (e.g., 'Legal' vs. 'Product'). Give them access to `get_action_items` and let them debate the feasibility of those tasks, forcing a consensus on what should actually happen.

Yes. The system can incorporate MCP tools from various servers into its debate pool. This means one agent can argue using data fetched from Tactiq's `list_meetings`, while another uses context from a different service.

Give it both `get_transcript` and `search_transcripts`. You can have one agent search for keywords, and a second agent analyze the retrieved context against known company policies, leading to a highly vetted conclusion.

No. It accepts any structured output—be it speaker lists, summaries, or action items—and treats that data as conversational evidence for the agents to argue over and analyze.

The first step is letting an agent run `check_tactiq_status`. This provides immediate, verifiable proof that all MCP tools are connected and ready to be used in the subsequent debates.

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