How to Use the Dovetail MCP in OpenAI Agents SDK

Q: How do I register the Dovetail MCP Server with my OpenAI Agents SDK pipeline?

You pass the server URL to the MCPServerStreamableHttp constructor and include it in your agent's server list. The SDK automatically discovers tools like listprojects at runtime. Enable cacheToolsList to avoid redundant network roundtrips during agent initialization.

Q: Can my OpenAI Agents SDK system create new research findings in Dovetail?

Yes, your pipeline uses createinsight to write synthesized findings back to your research projects. The agent handles the schema mapping automatically, using OpenAI's native validation to keep data clean. This replaces manual copy-pasting of user interview summaries.

Q: How does the Dovetail tool integration handle agent handoffs in OpenAI Agents SDK?

Your OpenAI Agents SDK client runs listnotes to gather customer quotes, using MCP to coordinate the handoff. A triage agent gathers the customer quotes, then hands the structured text to a specialized synthesis agent. The second agent processes the payload and calls createinsight to record the final theme.

Q: Why should I use cacheToolsList with Dovetail on OpenAI Agents SDK?

Caching prevents the SDK from querying the listprojects and other tool definitions on every single turn. It drops latency significantly when your agents run high-frequency synthesis loops. Your agent accesses the tools instantly without cold-start delays.

Feed raw Dovetail user research straight to your OpenAI Agents SDK pipelines with secure guardrails and zero-config tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect Dovetail to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Securely write research notes via OpenAI Agents SDK

The `create_note` tool lets your OpenAI Agents SDK pipeline write raw customer feedback directly into your research projects. You don't have to write manual parsing scripts because the agent maps raw transcripts to your workspace structure dynamically. This MCP Server integration uses OpenAI's built-in guardrails to check every note before it writes to your database. Your agent validates the input schema against your workspace parameters, stopping malformed transcripts from cluttering your historical data.

Sync research themes across specialized agents

The `list_insights` tool pulls verified user pain points so your OpenAI Agents SDK system can pass structured context between specialized product agents. Instead of dumping raw data, one agent extracts the patterns and hands them off to a downstream agent for feature mapping. You trace the entire synthesis path using the OpenAI dashboard to see exactly which customer quotes triggered a product decision. This visibility ensures your automated product managers don't fabricate user needs or ignore raw qualitative evidence.

Audit workspace access during synthesis runs

The `list_workspace_members` tool exposes active team directories to your MCP runtime. Your system checks this list to verify who owns a project before writing new findings or updating existing research repositories. By combining `get_project_details` with active member directories, your agents assign the correct researcher to newly generated findings. This setup keeps your workspace organized without requiring manual user mapping in your Python code.

Setup guide

Set up Dovetail MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Dovetail tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dovetail tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dovetail tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Dovetail Agent",
            instructions="You have access to Dovetail tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You pass the server URL to the `MCPServerStreamableHttp` constructor and include it in your agent's server list. The SDK automatically discovers tools like `list_projects` at runtime. Enable `cacheToolsList` to avoid redundant network roundtrips during agent initialization.

Yes, your pipeline uses `create_insight` to write synthesized findings back to your research projects. The agent handles the schema mapping automatically, using OpenAI's native validation to keep data clean. This replaces manual copy-pasting of user interview summaries.

Your OpenAI Agents SDK client runs `list_notes` to gather customer quotes, using MCP to coordinate the handoff. A triage agent gathers the customer quotes, then hands the structured text to a specialized synthesis agent. The second agent processes the payload and calls `create_insight` to record the final theme.

Caching prevents the SDK from querying the `list_projects` and other tool definitions on every single turn. It drops latency significantly when your agents run high-frequency synthesis loops. Your agent accesses the tools instantly without cold-start delays.

The SDK routes your qualitative research notes through a secure, ephemeral V8 sandbox that never retains your text. Your API credentials stay encrypted on Vinkius and never touch OpenAI's training datasets. You control access at the tool level, keeping raw participant interviews private.

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