Can my AI automatically reroute an assigned driver?

Yes. If an urgent delivery arises or a driver is delayed, you can prompt your agent to find another available fleet driver and assign them to the task. It bypasses the engine's built-in optimization logic and enforces the manual assignment on the Bringg dashboard globally.

Can I fetch the exact live location for a specific order?

Yes! Use the `get_task_timeline` tool. Your AI agent can query a specific task ID, reading the timeline progression as well as the active geolocation coordinates. This is perfect for support agents dealing with "Where is my order?" queries who don't want to open a secondary tab.

What happens if a driver forgets to mark a task complete on their app?

You can force the status progression using your AI agent. Tools like `force_task_complete` and `force_task_start` allow you to manually push the task into its finalized state inside your chat, instantly solving tracking desyncs for your logistics operation.

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

Name: Bringg
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 Bringg 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="bringg_agent",
    instruction=(
        "You help users interact with Bringg "
        "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 Bringg MCP Server

Connect your Bringg account to any AI agent and take full control of your final-mile delivery and dispatch operations through natural conversation.

Google ADK natively supports Bringg 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

Delivery Tasks — Create, update, list, and cancel delivery tasks dynamically before the truck leaves your hub
Fleet Dispatch — Manually assign specific drivers to tasks, bypassing default optimization algorithms
Live Timelines — Pull real-time geolocated tracking data and status estimates for any active order
Force Progression — Manually trigger task start or completion states to keep the dispatch board accurate
Driver CRM — List all human drivers across the fleet, track their availability, and analyze active limits
Customer Database — Instantly retrieve historical data for past delivery recipients

The Bringg 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 Bringg to Google ADK via MCP

Follow these steps to integrate the Bringg 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 Bringg via MCP

Why Use Google ADK with the Bringg MCP Server

Google ADK provides unique advantages when paired with Bringg 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 Bringg

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 Bringg tools with BigQuery, Vertex AI, and Cloud Functions

Bringg + Google ADK Use Cases

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

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

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

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

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

Bringg MCP Tools for Google ADK (10)

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

assign_driver_to_task

Manually override optimization and assign a specific driver to a task

cancel_task_dispatch

Cancel and permanently remove a delivery task from the dispatch schedule

create_delivery_task

Create a new delivery task (order) in the Bringg Delivery Hub

force_task_complete

Force a delivery task status to COMPLETE (successfully delivered)

force_task_start

Force a delivery task status to START (driver en route)

get_task_timeline

Retrieve comprehensive details and live timeline for a specific task

list_active_tasks

` mapping the SaaS dashboard directly isolating pending deliveries. Retrieve a paginated list of active delivery tasks/orders

list_customer_crm

List historical delivery recipients (customers) registered in Bringg

list_fleet_drivers

List all human drivers (users) within the Bringg fleet network

update_task_details

Modify existing delivery task details such as customer notes or dropoff info

Example Prompts for Bringg in Google ADK

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

"Show me the top 3 most recent active deliveries in the hub."

"Where is the order for Task ID 3109 and what's its exact timeline?"

"Force mark task 9481 as complete, the driver forgot to do it."

Troubleshooting Bringg MCP Server with Google ADK

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

McpToolset not found

Update: pip install --upgrade google-adk

Bringg + Google ADK FAQ

Common questions about integrating Bringg 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.