How to Use the Pelias Geocoder MCP in Google ADK

Q: What happens if a coordinate search returns multiple matching locations?

Your agent can use searchlayerfilter to narrow down the results by specific GIS layers. This helps the model decide whether a match represents a neighborhood, a street, or a specific venue.

Connect Gemini models to Pelias Geocoder with Google ADK to analyze spatial data directly alongside BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pelias Geocoder MCP to Google ADK

Create your Vinkius account to connect Pelias Geocoder to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pelias Geocoder with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Ground Gemini reasoning in real-world coordinates.

Enterprise agents built on Google ADK often struggle to translate raw database text into physical coordinates. This MCP Server links your Gemini model to the Pelias API, allowing it to translate address strings into latitude and longitude using `search_geocode`. Once the coordinates are resolved, your agent can write them back to BigQuery or use them to trigger localized workflows. The model uses `lookup_place_id` to fetch rich schema properties for specific venues, ensuring your spatial database remains clean and structured.

Run deep spatial analysis on Google ADK.

Long-context Gemini models excel at parsing massive datasets, but they need real-time location lookups to make sense of physical logistics. By calling `reverse_geocode` and `reverse_distance_limit` via the MCP Server, your agent identifies exactly what is located at specific GPS coordinates. This is perfect for processing fleet telemetry or delivery driver logs. The agent can take thousands of coordinate points and resolve them into actual street addresses, making it easy to generate clean reports directly inside your Vertex AI workspace.

Constrain enterprise search to specific regions.

Keep your Gemini agent focused on the regions your business actually serves. By applying `search_bounding_box` and `search_country_filter`, your agent ignores irrelevant global search results and focuses strictly on your defined service areas. This reduces token usage and prevents the model from getting lost in global map data. It uses `search_focus_bias` to prioritize locations near your distribution centers, ensuring that your automated logistics routing is both accurate and fast.

Setup guide

Set up Pelias Geocoder 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 Pelias Geocoder 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="Pelias Geocoder_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Pelias Geocoder 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 Pelias Geocoder. 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 Pelias Geocoder 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 Pelias Geocoder MCP in Google ADK

Use the McpToolset class and pass your Vinkius HTTP endpoint into the server parameters. When you initialize your LlmAgent, pass this toolset into the tools array, which instantly exposes operations like search_geocode to Gemini.

Yes, you can pass a list of allowed tool names to the toolset configuration. If you only want your agent to perform reverse lookups, you can expose reverse_geocode while hiding search_autocomplete entirely.

Gemini can feed large batches of address strings from BigQuery directly to the agent. The agent then calls structured_geocoding sequentially to parse and validate each address, maintaining high accuracy even when processing thousands of tokens of location data.

Your agent can use search_layer_filter to narrow down the results by specific GIS layers. This helps the model decide whether a match represents a neighborhood, a street, or a specific venue.

All coordinate pairs and address strings sent through this MCP Server are encrypted in transit. Vinkius executes the code in isolated V8 sandboxes that do not persist your enterprise GIS data or query histories to disk.

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