Can the agent calculate walking paths across multiple floors?

Yes. When triggering `calculate_path` supplied with explicit coordinate pairings spanning different Level UUIDs, the Pointr engine bridges the wayfinding automatically. It factors in fixed transitions like elevators or stairs natively, feeding the Agent the comprehensive turn-by-turn array in JSON format seamlessly.

Is it possible to extract the giant raw map shapes for a given floor?

Absolutely. By initiating the query `get_level_map` tied securely to a single level UUID, the interface processes and downloads massive explicit geometries mapping out physical walls, traversable space nodes, and internal partitions explicitly generated by the Pointr pipeline.

Can I search for specific stores or bathrooms using text queries?

Yes. Pointr exposes dense fuzzy logic matching indexes. When the Agent executes `search_pois` feeding a literal keyword alongside the Target Building ID, it reliably unearths precisely mapped nodes conforming to 'Restroom', 'Exit', or custom store names embedded dynamically.

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

Name: Pointr
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 Pointr 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="pointr_agent",
    instruction=(
        "You help users interact with Pointr "
        "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 Pointr MCP Server

Bring deep indoor location intelligence directly to your AI operations using the Pointr network. This MCP integration securely bridges your LLM to complex structural databases plotting multi-floor layouts, indoor geo-fencing, and Bluetooth Low Energy (BLE) beacon networks. Instead of navigating complicated dashboards to audit facility paths, simply instruct your local Agent to parse physical building parameters perfectly.

Google ADK natively supports Pointr 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

Facility Exploration — Understand global deployments natively. Run list_buildings and list_levels to mathematically visualize vertical architectures and floor limits.
Precision Wayfinding — Query active Point of Interest objects. The agent leverages search_pois to find specific gates/stores, and dynamically invokes calculate_path predicting multi-floor walking paths avoiding structural walls.
Infrastructure Auditing — Ask the AI to evaluate BLE hardware mesh footprints using the list_beacons utility, verifying precisely where physical network sensors reside inside map geometries.
Geo-Fence Parsing — Interrogate proactive indoor trigger zones. list_geofences brings back complex logical polygons mapping where local alerts fire globally.

The Pointr 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 Pointr to Google ADK via MCP

Follow these steps to integrate the Pointr 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 Pointr via MCP

Why Use Google ADK with the Pointr MCP Server

Google ADK provides unique advantages when paired with Pointr 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 Pointr

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 Pointr tools with BigQuery, Vertex AI, and Cloud Functions

Pointr + Google ADK Use Cases

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

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

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

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

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

Pointr MCP Tools for Google ADK (10)

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

calculate_path

Calculate the optimal indoor wayfinding path between two points

get_building

Retrieve detailed configuration for a specific Pointr building

get_level_map

Retrieve the floor plan map data for a specific building level

get_poi

Retrieve detailed information for a specific Pointr POI

list_beacons

List all BLE beacons deployed and registered in the Pointr platform

list_buildings

List all buildings registered in the Pointr indoor intelligence platform

list_geofences

List all indoor geofences configured in the Pointr platform

list_levels

List all floor levels for a specific Pointr building

list_pois

List all Points of Interest (POIs) registered in the Pointr platform

search_pois

Search for indoor Points of Interest by keyword

Example Prompts for Pointr in Google ADK

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

"List all active building deployments registered in our Pointr instance."

"Search for all restrooms securely listed under building ID `b1b2-c3c4`."

"Calculate indoor path from POI `poi_origin` to `poi_destination`."

Troubleshooting Pointr MCP Server with Google ADK

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

McpToolset not found

Update: pip install --upgrade google-adk

Pointr + Google ADK FAQ

Common questions about integrating Pointr 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.