How to Use the Local Falcon MCP in Google ADK

Q: How do I connect the Local Falcon MCP Server to my Google ADK agent?

You initialize McpToolset using your Vinkius HTTP transport URL. This exposes all 13 ranking tools through the MCP standard directly to Gemini, allowing it to execute functions like checklocalfalconstatus automatically.

Q: How do I restrict which Local Falcon tools my Google ADK agent can access?

You use the toolnames parameter in your McpToolset configuration to filter the exposed functions. For instance, you can limit a reporting agent to only use getscanresults and gettrendreport, blocking write operations.

Q: Can I retrieve the current status of my tracking setup?

Yes, your agent can call getlocation to check if a storefront is properly configured. It can also run listlocations to map out your entire active inventory before starting an MCP-driven scan.

Analyze geographic SEO performance across millions of tokens with Google ADK and Local Falcon.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Local Falcon MCP to Google ADK

Create your Vinkius account to connect Local Falcon 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 Local Falcon with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run high-density map scans with Google ADK

The `run_scan` tool initiates a geographical coordinate grid scan to capture precise local search rankings. For enterprise accounts managing thousands of locations, Gemini's massive context window can ingest these raw grid files to identify regional weak spots. By passing this toolset to your Google ADK agent, you connect Google Maps visibility data directly to your Vertex AI models. The model can then trigger `get_scan_results` to update your internal search indexes.

Sync Local Falcon data to Google Cloud

The `get_trend_report` tool extracts historical ranking changes to feed your enterprise data warehouse. Your agent can pull performance history and write it directly to BigQuery for cross-channel marketing analysis. Using `list_scans_by_location`, the agent tracks how specific storefronts perform over quarters. This turns raw ranking data into structured cloud assets that your BI tools can query instantly.

Programmatic location provisioning via MCP Server

The `add_location` tool adds new physical business addresses to your tracking dashboard in real time. Your enterprise agent can monitor your internal store registry and run this tool whenever a new location goes live. Once added, the agent executes `add_keyword` to bind target search queries to the new coordinates. This keeps your local SEO monitoring perfectly in sync with your physical retail footprint.

Setup guide

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

You initialize `McpToolset` using your Vinkius HTTP transport URL. This exposes all 13 ranking tools through the MCP standard directly to Gemini, allowing it to execute functions like `check_localfalcon_status` automatically.

Yes, Gemini's long-context window easily processes multiple outputs from `get_scan_report` simultaneously. Your Google ADK agent can compare historical trends across hundreds of locations in a single prompt.

You use the `tool_names` parameter in your `McpToolset` configuration to filter the exposed functions. For instance, you can limit a reporting agent to only use `get_scan_results` and `get_trend_report`, blocking write operations.

Yes, your agent can call `get_location` to check if a storefront is properly configured. It can also run `list_locations` to map out your entire active inventory before starting an MCP-driven scan.

Your business coordinates and keyword lists are processed in isolated, single-use V8 runtimes. Vinkius secures your Google ADK integration by routing all API requests through an encrypted proxy, preventing credential leakage.

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