Phonepi Mcp

Created By
maina year ago
Overview

What is PhonePi MCP?

PhonePi MCP is a powerful server and companion app that transforms your phone into a toolbox for AI assistants using the Model Context Protocol. It allows you to manage and control your phone remotely through natural language commands via MCP-supported AI applications like Cursor and Claude Desktop.

How to use PhonePi MCP?

To use PhonePi MCP, set up the server locally by following the instructions on the official documentation. You can then interact with your phone using natural language commands through compatible AI applications.

Key features of PhonePi MCP?

  • Manage contacts and messages
  • Handle snippets and notes
  • Control phone settings and notifications
  • Send SMS and make calls
  • Share content across apps
  • Monitor battery status
  • Set timers and reminders
  • Find your phone with audio alerts

Use cases of PhonePi MCP?

  1. Remotely manage your phone's contacts and messages using voice commands.
  2. Set reminders and timers without touching your phone.
  3. Control phone settings and notifications through AI assistants.

FAQ from PhonePi MCP?

  • Is PhonePi MCP secure?

Yes! The server is hosted locally, and you control the permissions and network security.

  • Can I use PhonePi MCP on any phone?

PhonePi MCP is designed to work with any phone that supports the necessary APIs.

  • Is PhonePi MCP open source?

Yes! The code is open source, and contributions are welcome.

Server Config

{
  "mcpServers": {
    "phonepi-mcp": {
      "command": "npx",
      "args": [
        "phonepi-mcp",
        "start"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
main
Star
-
Language
-
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
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)

a day ago