Google Maps MCP server for AI agents

Live

API KEY

LOCATION DATA

Productivity

Google Maps gives your agent location data: search places and read their details, geocode addresses and coordinates, validate postal addresses, and compute routes and travel time matrices.

  • Per-user credentials: each call uses the actual user's API key, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Google Maps
agent · Acme Q3
Run
Find coffee shops near Union Square in San Francisco.
S
googlemaps_places_search_text
88ms
Location agent
14 coffee shops match near Union Square. The top-rated one has a 4.7 rating and opens at 7am.
Sources: Google Maps places, 14 results
googlemaps
14 places
18:29
Message Claude...

Tools your location agent reaches for on Google Maps, scoped per user.

CALL ANY TOOL
14 tools for location data on Google Maps: search places and fetch details and photos, geocode and reverse geocode, validate addresses, snap GPS traces to roads, and compute routes.
googlemaps_address_validate
Validate address
Check and standardise a postal address, filling in missing parts and flagging components that look wrong. Returns a verdict (validation granularity, whether it's complete and whether parts were inferred or replaced), the corrected address, geocode, and USPS data for US addresses when requested, plus a responseId. Use this to verify a mailing or delivery address. Use geocode_address when you only need coordinates.
Parameters
Name
Type
Required
Description
address_lines
array
Required
The unstructured address lines, for example ["1600 Amphitheatre Pkwy", "Mountain View, CA 94043"]. You can put the whole address in one line. All address inputs together must be at most 280 characters.
administrative_area
string
Optional
State, province or region, if not already in address_lines. Example: CA.
enable_usps_cass
boolean
Optional
If true, also run USPS CASS validation (US and Puerto Rico addresses only); region_code must be US or PR. Defaults to false.
locality
string
Optional
City or town, if not already in address_lines. Example: Mountain View.
postal_code
string
Optional
Postal or ZIP code, if not already in address_lines. Example: 94043.
previous_response_id
string
Optional
The responseId from a previous validation of the same address, when re-validating after the user edits it. Leave empty for a new address.
region_code
string
Optional
Two-letter CLDR region code of the address, such as US or GB. Strongly recommended; if omitted Google infers it from the address lines.
session_token
string
Optional
Autocomplete session token to end an autocomplete session with this validation for billing. URL-safe base64, at most 36 characters.
googlemaps_geocode_address
Geocode address
googlemaps_geocode_location
Geocode location
googlemaps_geocode_place
Geocode place
googlemaps_geolocate
Geolocate
googlemaps_places_autocomplete
Places autocomplete
googlemaps_places_get
Get places
googlemaps_places_photo_get
Get places photo
googlemaps_places_search_nearby
Places search nearby
googlemaps_places_search_text
Places search text
googlemaps_roads_nearest_roads
Roads nearest roads
googlemaps_roads_snap_to_roads
Roads snap to roads
googlemaps_routes_compute
Routes compute
googlemaps_routes_compute_matrix
Routes compute matrix
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Google Maps tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlemaps"], toolNames: [
    "googlemaps_geocode_address",
    "googlemaps_places_search_nearby",
    "googlemaps_routes_compute"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find coffee shops within 500 meters of 333 Post Street and get walking directions to the closest one" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlemaps"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find coffee shops within 500 meters of 333 Post Street and get walking directions to the closest one" }],
  tools,
});

// Execute the tool call with the user's vaulted Google Maps API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlemaps"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find coffee shops within 500 meters of 333 Post Street and get walking directions to the closest one" }],
  tools,
});

// Tool call runs with the user's vaulted Google Maps API key
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlemaps"] }, pageSize: 100,
});

const agent = new Agent({
  name: "location_agent",
  model: "gemini-2.5-pro",
  instruction: "Google Maps tools scoped to this user",
  tools,
});

await agent.run("Find coffee shops within 500 meters of 333 Post Street and get walking directions to the closest one");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Google Maps tool. Click to copy, paste into your agent, done.
Places
Copy the prompt
Copied
Find Italian restaurants near the Ferry Building with a rating above 4.5.
Copy the prompt
Copied
Get the opening hours and phone number for this place ID.
Copy the prompt
Copied
Suggest places as I type blue bottle mis.
Addresses
Copy the prompt
Copied
Validate this shipping address: 1600 Amphitheatre Pkwy, Mountain Vew CA.
Copy the prompt
Copied
Get the latitude and longitude for 221B Baker Street, London.
Copy the prompt
Copied
What address is at 40.7484, -73.9857?
Routes
Copy the prompt
Copied
How long is the drive from SFO to Palo Alto right now with traffic?
Copy the prompt
Copied
Compute travel times from our 3 warehouses to these 10 customer addresses.
Copy the prompt
Copied
Snap this GPS trace from the delivery van to the roads it drove.
SEE HOW AUTH WORKS
Each user connects their own Google Maps API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Google Maps
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Google Maps
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Google Maps
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Google Maps
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other search and productivity connectors.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
Test other agents
See the same per-user auth pattern across other search and productivity connectors.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
SALES
Outbound prospecting agent
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Google Maps API key looks fine in a demo. In production every place search and route request looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Google Maps today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Google Maps as the user or through a shared key?
As the user. Each user connects their own Google Maps API key once, and Scalekit sends it with every call. Place searches and route requests are attributed to that user in your audit trail, not a shared service account.
Where is the Google Maps API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Google Maps?
Yes. Every Google Maps tool is read-only, so the agent cannot change anything. You can still filter by tool name in listScopedTools, for example to expose the places and geocoding tools without the roads and route matrix tools. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Google Maps access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Does the agent need coordinates to search for places?
No. googlemaps_places_search_text takes a free-text query such as pizza in New York and returns up to 20 places per page. googlemaps_places_search_nearby searches a circle around a latitude and longitude, which the agent can get from googlemaps_geocode_address.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""googlemaps"": {
""url"": ""https://mcp.scalekit.com/googlemaps"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.googlemaps]
url = ""https://mcp.scalekit.com/googlemaps""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""googlemaps"": {
""url"": ""https://mcp.scalekit.com/googlemaps"",
""type"": ""http""
}
}
}