Can I automatically trigger an RPA task via the AI agent?

Yes! Use the `trigger_task` tool with the target Robot ID and any required input parameters. Your agent will start the automation job and return the unique Job ID.

How do I check if a robot is currently online and ready?

Use the `list_robots` tool. It will retrieve all configured robots in your ShadowBot account along with their current status (e.g., Online, Busy, Offline).

Can I retrieve the logs for a completed automation job?

Yes! The `get_task_logs` tool allows you to fetch the execution details and any output data for a specific Job ID.

ShadowBot MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: ShadowBot
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add ShadowBot as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="shadowbot_agent",
    instruction=(
        "You help users interact with ShadowBot "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About ShadowBot MCP Server

Connect your AI agents to ShadowBot (影刀RPA), the leading Robotic Process Automation (RPA) platform for high-performance browser and desktop automation. This MCP provides 10 tools to manage automation robots, orchestrate execution tasks, and monitor the health of your digital workforce programmatically.

Google ADK natively supports ShadowBot as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Robot Orchestration — List and inspect available automation robots and their current operational status
Task Execution — Trigger specific automation tasks and handle job lifecycle management from start to finish
Performance Monitoring — Retrieve granular execution logs and track robot throughput and success rates
Credential Handling — Monitor and manage robotic account assignments and access tokens for secure automation
Global Management — Access organizational project structures and list active automation workflows directly from your agent

The ShadowBot MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect ShadowBot to Google ADK via MCP

Follow these steps to integrate the ShadowBot MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from ShadowBot via MCP

Why Use Google ADK with the ShadowBot MCP Server

Google ADK provides unique advantages when paired with ShadowBot through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with ShadowBot

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine ShadowBot tools with BigQuery, Vertex AI, and Cloud Functions

ShadowBot + Google ADK Use Cases

Practical scenarios where Google ADK combined with the ShadowBot MCP Server delivers measurable value.

Enterprise data agents: ADK agents query ShadowBot and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine ShadowBot tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query ShadowBot regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including ShadowBot

ShadowBot MCP Tools for Google ADK (10)

These 10 tools become available when you connect ShadowBot to Google ADK via MCP:

get_robot_details

Get detailed information for a specific robot

get_task_details

Retrieve the status and results of a ShadowBot task

list_apps

List all RPA applications in your ShadowBot account

list_department_members

List members in a specific department

list_departments

Retrieve the organizational department list

list_online_robots

List currently online robots

list_robots

List all robots associated with the account

list_task_logs

Retrieve logs for a specific task

start_task

Remote trigger a ShadowBot RPA application

stop_task

Stop a running ShadowBot task

Example Prompts for ShadowBot in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with ShadowBot immediately.

"List all automation robots in my ShadowBot account and show their status."

"Start task 'process_invoices' on robot ID 'bot_rpa_777'."

"Get the execution logs for Job ID 'job_12345'."

Troubleshooting ShadowBot MCP Server with Google ADK

Common issues when connecting ShadowBot to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

ShadowBot + Google ADK FAQ

Common questions about integrating ShadowBot MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.