How to Use the Plecto MCP in Google ADK

Q: How do I set up the Plecto MCP server with Google ADK?

After installing the ADK, create an McpToolset instance pointing to your Vinkius server URL. Then, pass that toolset into the tools argument when you create your LlmAgent.

Q: Can a Google ADK agent analyze Plecto formula logic?

Yes. The agent can call listformulas to get a list of all KPI formulas in your Plecto account. This is useful for agents that need to understand how a specific metric is calculated before they act.

Q: How can I limit which Plecto tools my Google ADK agent can use?

When you create the McpToolset, you can use the toolnames filter. Provide a list of tool names, like 'createdataregistration', to restrict the agent to only those specific actions.

Let your Google ADK agents update Plecto dashboards. Connect your Gemini models to your sales data and KPIs without leaving the Google Cloud ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plecto MCP to Google ADK

Create your Vinkius account to connect Plecto 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 Plecto with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Trigger Plecto Updates from BigQuery

This is the bridge between your Google Cloud data and your Plecto dashboards. Your ADK agent can analyze data in BigQuery, and when a threshold is met, it calls `create_data_registration` to push a new entry into Plecto. Think of it as turning your data warehouse into a real-time event source for your sales floor. Because you're using Gemini models, your agent has a massive context window. It can analyze complex business logic before deciding to update a Plecto KPI. It's not just a simple trigger; it's a reasoning engine that acts on your data.

Build Enterprise Reporting with Google ADK

Your Google ADK agent can build reports on your Plecto setup. It can fetch all dashboards with `list_kpi_dashboards`, check their widgets with `list_widgets`, and then grab the underlying data with `list_data_registrations`. It's all the information you need to audit your KPI reporting infrastructure. You can feed this structured data back into other Google services. For instance, have the agent pull Plecto data and generate a summary in a Google Doc. This MCP server makes Plecto another connected service in your GCP environment.

Manage Team Performance Data

Automate how you manage your sales teams' performance data. Your agent can get a full roster using `list_account_employees` and cross-reference it with your HR database. If it finds a mismatch, it can flag it for review. You can also build agents that provide on-demand stats. A manager could ask the agent to pull performance data for a specific person using `get_employee` and `get_registration`, giving them instant access without having to navigate the Plecto UI.

Setup guide

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

After installing the ADK, create an `McpToolset` instance pointing to your Vinkius server URL. Then, pass that toolset into the `tools` argument when you create your `LlmAgent`.

Yes. The agent can call `list_formulas` to get a list of all KPI formulas in your Plecto account. This is useful for agents that need to understand how a specific metric is calculated before they act.

No, your Plecto data stays in Plecto. The Google ADK agent makes secure calls to the Vinkius-hosted MCP server, which then interacts with the Plecto API. Data is only moved when your agent explicitly calls a tool.

When you create the `McpToolset`, you can use the `tool_names` filter. Provide a list of tool names, like `['create_data_registration']`, to restrict the agent to only those specific actions.

Yes. The connection is handled by the Vinkius MCP server, which uses your unique endpoint token for authentication. The ADK agent simply invokes the tools; it doesn't get direct access to your Plecto credentials, and data like registrations is sandboxed.

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