How to Use the Lindy (Autonomous AI Employees) MCP in Google ADK

Q: How do I manage third-party app connections in Lindy (Autonomous AI Employees) via Google ADK?

You query listintegrations to verify which external apps are securely connected to your workspace. This allows your Google ADK to confirm that communication channels like Slack or Gmail are active before triggering a run.

Q: How does this MCP Server handle multi-team isolation?

The server uses listworkspaces to define strict organizational boundaries. Your agent queries this tool to ensure that tasks triggered by Google ADK never cross into unauthorized team environments.

Q: Is my workspace integration data safe with this MCP setup?

Your actual credentials for tools listed in listintegrations never touch the LLM. This MCP Server only shares connection status metadata with Google ADK, while the execution itself runs inside Vinkius's zero-trust sandbox.

Control autonomous Lindy employees directly from Gemini using Google ADK and enterprise BigQuery pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lindy (Autonomous AI Employees) MCP to Google ADK

Create your Vinkius account to connect Lindy (Autonomous AI Employees) 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 Lindy (Autonomous AI Employees) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Lindy tasks using Google ADK and Gemini

The `trigger_lindy` tool lets your Google ADK pass payloads from BigQuery directly to autonomous employees to start asynchronous execution runs. Gemini uses its long-context window to evaluate the running state via `get_run` when operations halt for human sign-offs. When an execution goes off track, Google ADK calls `cancel_run` to terminate the loop instantly. This keeps your enterprise cloud workflows predictable and prevents runaway compute costs on Google Cloud.

Audit execution logs inside your Google ADK pipeline

The `get_run_logs` tool extracts raw LLM reasoning steps so your Google ADK can inspect how an autonomous employee made a specific decision. This allows Gemini to analyze complex multi-step failures using your existing Google Cloud monitoring tools. You can list all active executions with `list_runs` to keep a clean audit trail of every agent action. Your Google ADK matches these logs against BigQuery datasets to verify operational consistency across your entire department.

Discover workspace configurations with this MCP Server

The `list_lindies` tool feeds your Google ADK a clean directory of all custom autonomous employees built on your workspace. Gemini reads specific agent prompts and tool configurations using `get_lindy` to determine the best agent for a given task. The MCP Server exposes system triggers via `list_triggers` and team boundaries via `list_workspaces`. This lets your Google ADK manage complex enterprise schedules, ensuring tasks run only within designated organizational units.

Setup guide

Set up Lindy (Autonomous AI Employees) 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 Lindy (Autonomous AI Employees) 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="Lindy (Autonomous AI Employees)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Lindy (Autonomous AI Employees) 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 Lindy. 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 Lindy (Autonomous AI Employees) 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 Lindy (Autonomous AI Employees) MCP in Google ADK

Your Google ADK connects to the MCP Server to discover tools like `trigger_lindy` and `list_runs`. Gemini uses these tools to launch background tasks and monitor their execution states directly from your Google Cloud environment.

Yes, Gemini can read the exact reasoning paths. By invoking `get_run_logs` through the Google ADK, your agent retrieves the raw LLM thought process to diagnose why a specific run stalled or failed.

You query `list_integrations` to verify which external apps are securely connected to your workspace. This allows your Google ADK to confirm that communication channels like Slack or Gmail are active before triggering a run.

The server uses `list_workspaces` to define strict organizational boundaries. Your agent queries this tool to ensure that tasks triggered by Google ADK never cross into unauthorized team environments.

Your actual credentials for tools listed in `list_integrations` never touch the LLM. This MCP Server only shares connection status metadata with Google ADK, while the execution itself runs inside Vinkius's zero-trust sandbox.

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