Sign in Book a demo
Back to Tools
Search API Key BYOCPro
Build Your Agent View Google Maps Docs
google-maps logo

Google Maps MCP Tools for AI Agents

Let an agent get directions between addresses or latitude and longitude coordinates through Arcade's MCP gateway.

Available Tools

2 tools available in this integration

GoogleMaps.GetDirectionsBetweenAddresses

Get directions from Google Maps.

GoogleMaps.GetDirectionsBetweenCoordinates

Get directions from Google Maps.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "get directions from our office to the customer's warehouse." Arcade helps it use the right Google Maps capability without guessing whether the locations are street addresses or coordinates.

Up to 100x fewer tokens

Google Maps returns a focused directions response for the two locations instead of making the agent load a broad map dataset. The model gets the route information it needs without carrying unrelated map content.

Complete the workflow end to end

Read the travel request, identify the origin and destination, use addresses or coordinates, get directions, and return the route through one toolkit designed around the complete routing task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Google Maps

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Google Maps, you can implement some of these policies:

Access when tools are listed for a user
  • Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
Pre-execution before each tool call
  • Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
Post-execution after the tool returns
  • Redact street numbers and apartment or unit details from GoogleMaps.GetDirectionsBetweenAddresses results before the model sees them, so an agent cannot retain precise residential locations in its context.
  • Strip exact latitude and longitude from GoogleMaps.GetDirectionsBetweenCoordinates results before the model sees them, so route guidance does not expose a person's precise location.

How to use Google Maps with your agent

Pick your MCP client below and follow the setup to connect Google Maps and start asking for directions.

Your questions, answered

A Google Maps MCP server exposes mapping capabilities as structured tools that an AI agent can call through the Model Context Protocol. With Arcade, the agent can request driving directions between street addresses or geographic coordinates.

Google Maps does not provide a first-party MCP server for these direction requests. Arcade hosts the integration and adds the runtime around it, including shared-key authentication, approval policies, redaction, and access from supported MCP clients.

Arcade agents can get directions between two street addresses or between two sets of geographic coordinates. The coverage does not include place search, geocoding, map imagery, traffic lookups, or other Google Maps actions.

Arcade uses a shared Google Maps API key or secret configured once for the integration. That credential must have access to the Google Maps directions capability; these actions do not require each user to grant Google OAuth scopes.

No. Users do not each connect a separate Google Maps account for this integration. One shared API key or secret is configured once, brokered by Arcade, and never passed to the model.

Yes. Contextual Access policies can require human approval before a Google Maps call proceeds. Both available actions are read-only direction lookups, so there is no write or destructive Google Maps action in this toolkit that requires approval by default.

Arcade proxies Google Maps API calls and does not persist your content as part of normal tool execution. The shared credential is brokered and stored encrypted at rest, and the model never receives it.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade continues using the shared credential while it remains valid. If the key is revoked, rotated, disabled, or can no longer be used, direction requests stop until the credential is updated or reconnected.

Google Maps Platform quotas, rate limits, billing settings, and project-level restrictions still apply to requests made through Arcade. Arcade does not remove Google's limits on directions requests.

Ready to actually ship your agent?

Connect your agent to Google Maps with a shared API key, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Google Maps Quickstart