# Google Maps MCP connector The Google Maps connector lets Claude, ChatGPT, Cursor, and the Elaichi Agent validate street addresses and compute routes and drive times through Elaichi, with each request logged under the person who made it. Source: https://elaichi.ai/connectors/googlemaps/ ## Facts | | | | --- | --- | | Application | Google Maps | | Category | Default | | AI tools | 3 | | Authentication | Connects with an API key | | Needs your own OAuth app | No | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | | Tools advertised by name | Yes | ## What you can ask once Google Maps is connected - Validate these 40 delivery addresses and flag the bad ones. - Compute routes from the depot to today's five stops. - Which addresses failed validation for the Logistics team this week? ## Connect Google Maps in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Google Maps. 2. Optionally set Share with, then press Connect. 3. Paste a Google Maps API key. One person generates a token in Google Maps and pastes it once. Everyone else works through Share with, and never sees it. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Google Maps tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Connect Google Maps to Claude Endpoint: https://api.elaichi.ai/mcp 1. Open Customize, then Connectors. 2. Press Add. 3. Name it, paste the MCP server URL, then Continue. 4. Sign in and approve. On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves. ## Connect Google Maps to ChatGPT Endpoint: https://api.elaichi.ai/mcp 1. Open Plugins, then press the + button. 2. Name it and paste the endpoint into Server URL. 3. Leave Authentication on OAuth, then tick the risk acknowledgement. 4. Press Create, then sign in and approve. Works on the web today. The plugin directory lives at chatgpt.com/plugins. ## Connect Google Maps to Cursor Endpoint: https://api.elaichi.ai/mcp 1. Open `~/.cursor/mcp.json`. 2. Add the endpoint under `mcpServers`. 3. Reload Cursor, then sign in and approve. Set up per machine, so repeat it on each computer you work from. ## Connect Google Maps to any MCP client Endpoint: https://api.elaichi.ai/mcp 1. Add the endpoint as a remote MCP server. 2. Sign in and approve. The Elaichi Agent already has these tools, with nothing to set up. ## What the consent screen decides Only Read is granted by default, which is not enough to call a Google Maps tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone. ## What teams do with Google Maps through Elaichi ### Clean up shipping addresses before labels print Operations. Paste a batch of customer addresses and have Google Maps confirm each one is real, deliverable, and formatted the way carriers expect, with corrections suggested where a unit number or postal code is missing. ### Check drive time before booking a visit Sales. Ask how long it takes to get from the office to a prospect's site at a given departure time, then pick a meeting slot that actually works. ### Confirm an address while the customer is on the line Support. Read back a corrected, validated address during a ticket so a replacement order goes to the right door the first time. ### Plan the day's delivery stops Logistics. Give the agent the morning's stops and get a route with distances and travel times between them, ready to hand to the driver. ### Route technicians between appointments Field service. Work out travel time between a technician's jobs so the schedule leaves room to get from one site to the next. ### Tell Google Maps when a correction was wrong Data quality. When a validated address turns out to be right or wrong in practice, send that feedback back to Google Maps so future checks improve. ## Frequently asked questions ### How do I connect Google Maps to Claude? Connect Google Maps in Elaichi first: you paste in your Google Maps API key, and there is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Sign in to Elaichi when Claude asks, and Google Maps address validation and routing are available in your conversation. ### Does Google Maps work with ChatGPT and Cursor as well as Claude? Yes. Once Google Maps is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent. You connect Google Maps once and every client you sign in to can use it. ### What can an AI agent actually do with Google Maps? Through this connector an agent can check whether a street address is real and complete, suggest the corrected version, and work out routes with distance and travel time between two or more places. It can also send feedback to Google Maps about whether a suggested address correction turned out to be right. It cannot search for businesses or edit anything in Google Maps, because this connector only covers address validation and routing. ### Does connecting Google Maps give the AI unlimited use of my API key? No. Requests to Google Maps run through the key the connecting person supplied, so anything that key cannot do, the agent cannot do either. Elaichi can narrow that further by turning off individual actions such as route computation or address feedback for a team, and it never widens what the key allows. ### Can my team share one Google Maps connection? Yes. One person connects Google Maps with the API key and shares the connection with a team in Elaichi, and nobody else ever sees or handles the key. Each teammate still signs in to Elaichi as themselves, so every address check and route request in the audit log names the person who made it. ### Can I stop an agent from doing certain things in Google Maps? Yes. Restrictions in Elaichi work per action, so you can allow address validation while blocking route computation or validation feedback, for example. A blocked action is never shown to Claude, ChatGPT, or Cursor at all, so no prompt can reach it. ### What happens to a Google Maps connection when someone leaves? Offboarding the person in Elaichi ends their access to Google Maps at once, across every client they used. If they connected Google Maps and shared it with a team, the shared connection keeps working for everyone else. Disconnecting Google Maps once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client in one step. ## All 3 Google Maps tools Every tool below is callable through https://api.elaichi.ai/mcp once Google Maps is connected, subject to the toolbox it is in and the restrictions on the caller. - **Google Maps address validation validate address** (Validate). Validate a postal address using Google Maps Address Validation API. Returns the validation result including verdict flags, the post-processed address with components, geocode with coordinates and place ID, deliverability metadata, and USPS data for US/PR addresses. Required: address (with addressLines). - **Google Maps address validation provide validation feedback** (Action). Provide feedback about the outcome of a sequence of address validation attempts in Google Maps Address Validation API. This should be the last call made after a sequence of validation calls for the same address, and should be called once the transaction is concluded. Returns an empty 204 response on success. Required: conclusion, responseId. - **Google Maps routes compute routes** (Action). Compute routes between an origin and a destination using the Google Routes API. Returns: duration, distanceMeters, polyline, legs, warnings, routeLabels. Required in body: origin, destination. Select fields with field_mask.