How to Use the Planhat MCP in Google ADK

Q: How do I connect the Planhat server to my Google ADK agent?

You'll use the McpToolset from the ADK library, pointing it to your Vinkius server URL. The agent discovers and gains access to all the Planhat tools instantly. You can also provide a toolnames filter to expose only specific tools.

Q: Can I analyze Planhat user activity with Google ADK?

Yes. Your agent calls listplanhatendusers to get the raw data. You can then instruct the agent to analyze it directly or pipe the output into a BigQuery table for more complex business intelligence work.

Q: How can I build a churn prediction model with Planhat and Google ADK?

Start by having your agent fetch training data. It can use listplanhatcompanies, listplanhatconversations, and listplanhatlicenses to collect the features you need for a model in Vertex AI. The agent handles the data collection for you.

Connect Planhat to your Google Cloud ecosystem. Let your Google ADK agent pull customer data for analysis in BigQuery or for summarization by Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Planhat MCP to Google ADK

Create your Vinkius account to connect Planhat to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Planhat with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Pull Planhat Data for BigQuery

This is your agent's bridge to Planhat. It can call `list_planhat_companies` or `list_planhat_end_users` to get a complete data dump. From there, your agent can load it straight into a BigQuery table for large-scale analysis. Because Gemini models can handle huge contexts, you don't have to worry about overwhelming your agent. It can pull thousands of records from Planhat, find the exact information you need, and structure it for your data warehouse.

Prep for Enterprise QBRs

Your Google ADK agent can build a complete account brief in seconds. It pulls project updates with `list_planhat_projects`, recent CSM activity with `list_planhat_notes`, and key discussions from `list_planhat_conversations`. All this information feeds directly into the agent's context window. It gives Gemini the raw material to generate a concise, data-driven summary of account health, risks, and opportunities before you even open the Planhat app.

Let your Google ADK Agent Run Point

Give your agent a direct line to your customer operations data. It can check on license utilization with `list_planhat_licenses` and see all open action items with `list_planhat_tasks` in a single query. This MCP Server provides the ground truth from your CS platform. Your Gemini-powered agent gets the facts from Planhat before it acts, whether that's querying other Google Cloud services or flagging an account for human review.

Setup guide

Set up Planhat 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 Planhat 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="Planhat_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Planhat 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 Planhat. 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 Planhat 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 Planhat MCP in Google ADK

You'll use the `McpToolset` from the ADK library, pointing it to your Vinkius server URL. The agent discovers and gains access to all the Planhat tools instantly. You can also provide a `tool_names` filter to expose only specific tools.

Yes. Your agent calls `list_planhat_end_users` to get the raw data. You can then instruct the agent to analyze it directly or pipe the output into a BigQuery table for more complex business intelligence work.

Start by having your agent fetch training data. It can use `list_planhat_companies`, `list_planhat_conversations`, and `list_planhat_licenses` to collect the features you need for a model in Vertex AI. The agent handles the data collection for you.

It's faster. This managed MCP server is already built, secured, and ready to go. You just give your agent a URL, and it starts working. You skip writing, hosting, and maintaining your own API wrapper code.

The server only touches the Planhat data your agent explicitly requests, like company names or user lists. Vinkius runs the server in an isolated sandbox with a single-use token. No data is ever stored, and the entire environment is wiped after the job is done.

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