How to Use the Dovetail MCP in AutoGen

Q: How do AutoGen agents access Dovetail MCP tools?

Install autogen-extmcp and use mcpservertools with your server URL to expose Dovetail capabilities to your AutoGen agents. Pass the resulting tool list directly to your AssistantAgent constructor.

Q: Can AutoGen agents map Dovetail workspace members to projects?

Your AutoGen agents call listworkspacemembers and cross-reference the output with getprojectdetails to assign tasks. This automates team allocation inside your Dovetail workspace.

Let AutoGen agents debate and synthesize Dovetail research data to reach consensus on product features.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dovetail MCP to AutoGen

Create your Vinkius account to connect Dovetail 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 Dovetail with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run AutoGen debates on raw Dovetail user feedback

The `list_notes` tool supplies your AutoGen agents with raw Dovetail customer quotes to drive multi-agent debates. Your agents analyze these notes from different perspectives. This debate ensures your AutoGen team reaches a consensus-driven analysis of Dovetail user pain points. You get balanced summaries without human bias.

Automate Dovetail research peer review with AutoGen

The `create_insight` tool lets your AutoGen writer agent propose new entries for peer review before publishing to Dovetail. Your reviewer agent then checks the draft. Your AutoGen reviewer agent checks the proposal against `get_project_details` before committing the final write to Dovetail. This negotiation keeps errors out of your workspace.

Deploy consensus-driven AutoGen agents with the MCP Server

The `list_workspace_members` tool lets your AutoGen agents coordinate tasks by identifying team ownership within Dovetail via this MCP Server. Your agents assign tasks dynamically. Using `mcp_server_tools` ensures your AutoGen agents can call `list_projects` to coordinate active Dovetail research sweeps. You run complex workflows without custom parsers.

Setup guide

Set up Dovetail 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 Dovetail 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="Dovetail_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your server URL to expose Dovetail capabilities to your AutoGen agents. Pass the resulting tool list directly to your `AssistantAgent` constructor.

Yes, one AutoGen agent can draft a note while another reviews it, finally calling `create_note` once they reach consensus on the Dovetail feedback.

The McpToolAdapter automatically translates the Dovetail MCP Server tool schemas into the format AutoGen expects. You do not need to write custom JSON schemas for your AutoGen agents.

Your AutoGen agents call `list_workspace_members` and cross-reference the output with `get_project_details` to assign tasks. This automates team allocation inside your Dovetail workspace.

Your qualitative Dovetail research data, including user quotes and synthesized insights, remains completely isolated during AutoGen multi-agent runs. The Vinkius platform runs the server in an ephemeral sandbox, preventing leakages of proprietary Dovetail feedback.

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