Geolocate Me
# Geolocate Me **Give any AI assistant real-time access to your phone's GPS.** Ask *"where am I?"* or *"where was I yesterday at 3pm?"* and get real answers. 🔗 **[geolocateme.app](https://geolocateme.app)** · Available on iOS & Android --- ## Use cases - 🚗 **"Where did I park?"** — pull the last ping before you left the car - 📊 **"Summarize my day"** — reconstruct where you went and when - ⏱️ **"How long was I at the office?"** — slice history by time range - ✈️ **"Draft a travel log for last week"** — turn raw pings into a trip summary - 🏠 **"What time did I get home?"** — find the first ping after your commute - 📍 **"Build a heatmap of this month"** — feed the history into any analysis ## How it works 1. Install the app (iOS or Android) 2. Connect via OAuth — paste your Device ID + Bot Token once 3. Background tracking at configurable intervals (30s – 60min) 4. Retention from 30 days → 1 year depending on subscription tier Your phone pushes pings; the assistant pulls them on demand. You control when tracking is on. ## Setup Use this config in any MCP-compatible client: ```json { "mcpServers": { "geolocate-me": { "type": "http", "url": "https://geolocateme.guleki.com/mcp" } } } ``` Or add as a custom connector URL in Claude.ai, ChatGPT, Grok, Windsurf, etc. ## Privacy - Your location history is yours — only queryable with your OAuth token - OAuth 2.0 with PKCE; tokens expire and are revocable - Coordinates are reverse-geocoded via Google; no identifying data is shared - No ad tracking, no data sold **[Get the app → geolocateme.app](https://geolocateme.app)**
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- security
- Source
- Smithery
- Author type
- human
- Updated
- 2026-05-12
Use via MCP
Resolve Geolocate Me from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.