How to Use the Dovetail MCP in Google ADK

Q: How do I connect the Dovetail MCP Server to my Google ADK agent?

You initialize McpToolset with your HTTP server parameters and pass it to the LlmAgent tools list. The ADK automatically exposes tools like listnotes to your Gemini model. You can run this setup on Vertex AI or local development environments.

Q: Can I filter which Dovetail tools are exposed to Google ADK?

Yes, you use the toolnames parameter in your McpToolset config to restrict access. For example, you can expose listinsights while blocking creation tools to keep your data read-only. This protects your workspace from accidental modification by autonomous agents.

Q: How does Gemini's long context benefit Dovetail synthesis in Google ADK?

Gemini ingests your entire history of raw notes via listnotes in a single prompt. The model analyzes thousands of user quotes simultaneously instead of processing them in small, disconnected batches. This results in highly accurate theme discovery across your entire workspace.

Feed Dovetail user research into Google ADK pipelines to synthesize qualitative data with Gemini's million-token context.

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 Google ADK

Create your Vinkius account to connect Dovetail to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject user notes into Google ADK long-context runs

The `list_notes` tool pulls thousands of customer feedback records directly into your Google ADK runtime environment. Gemini models ingest this entire qualitative dataset in a single turn, finding hidden patterns that shorter context windows miss. This MCP Server integration connects your research repository to BigQuery pipelines without complex ETL setups. Your agent queries raw notes, identifies trends, and pushes structured results back to your database using native Google Cloud infrastructure.

Map enterprise project metadata with Google ADK

The `get_project_details` tool retrieves deep workspace configurations so your Google ADK agent knows exactly where to write new findings using the MCP standard. Your enterprise pipeline matches these project details with existing customer records stored in Vertex AI. By running `list_projects` alongside your cloud database queries, the agent keeps your research taxonomy perfectly aligned. You don't have to hardcode project IDs or manually map workspace structures in your Python code.

Write synthesized insights back to Dovetail

The `create_insight` tool allows your Google ADK pipeline to write fully analyzed themes back to your research workspace. After Gemini processes a massive batch of raw interview transcripts, the agent records the final synthesized findings automatically. You restrict which tools the agent can access by passing a targeted tool list to your `McpToolset` configuration. This prevents autonomous cloud agents from altering critical project structures while allowing them to write new research findings.

Setup guide

Set up Dovetail MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Dovetail tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Dovetail_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Dovetail tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You initialize `McpToolset` with your HTTP server parameters and pass it to the `LlmAgent` tools list. The ADK automatically exposes tools like `list_notes` to your Gemini model. You can run this setup on Vertex AI or local development environments.

Yes, you use the `tool_names` parameter in your `McpToolset` config to restrict access. For example, you can expose `list_insights` while blocking creation tools to keep your data read-only. This protects your workspace from accidental modification by autonomous agents.

Yes, the ADK handles both Stdio and HTTP transports to connect with this MCP host. Most production deployments on Google Cloud use the streamable HTTP transport for better scalability. You get stable connections regardless of your hosting architecture.

Gemini ingests your entire history of raw notes via `list_notes` in a single prompt. The model analyzes thousands of user quotes simultaneously instead of processing them in small, disconnected batches. This results in highly accurate theme discovery across your entire workspace.

Your qualitative research insights are processed inside a zero-trust, isolated runtime that encrypts all transit data. Vinkius manages the authentication tokens securely, so your Google Cloud environment never exposes your workspace keys. No customer transcripts are used for public model training.

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