Geolocate Me

Created By
Charlie Linville2 months ago
Give any AI assistant real-time access to your phone's GPS. Ask "where am I?", "where did I park?", or "where was I yesterday at 3pm?" and get real answers. Install the iOS or Android app, connect once with OAuth, and your location is yours to query in natural language.
Overview

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 · 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:

{
  "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

Server Config

{
  "mcpServers": {
    "geolocate-me": {
      "type": "http",
      "url": "https://geolocateme.guleki.com/mcp"
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
Charlie Linville
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago