Claude MCP Approval Server

Created By
adstastica year ago
MCP server with Whatsapp integration (Twilio) to remote approve Claude Code tool use
Overview

What is Claude MCP Approval Server?

Claude MCP Approval Server is a Model Context Protocol (MCP) server that integrates with WhatsApp via Twilio to facilitate remote approval of commands executed by the Claude Code tool, enhancing security and control over sensitive operations.

How to use Claude MCP Approval Server?

To use the server, set up a Twilio account, configure your environment with the necessary credentials, and run the server. When a command is executed, you will receive an approval request via WhatsApp, allowing you to approve or deny the action.

Key features of Claude MCP Approval Server?

  • 🔐 Permission Prompts: Intercepts tool executions and requests approval via WhatsApp.
  • 📱 WhatsApp Integration: Utilizes Twilio for sending approval requests with quick-reply buttons.
  • FastMCP: Built on FastMCP for seamless integration with Claude.
  • ⏱️ Auto-expiry: Requests expire after 5 minutes for added security.
  • 💾 Database Tracking: Uses SQLite to track approval requests.

Use cases of Claude MCP Approval Server?

  1. Approving sensitive commands remotely via WhatsApp.
  2. Enhancing security for automated tools by requiring user confirmation.
  3. Tracking command approvals and denials for auditing purposes.

FAQ from Claude MCP Approval Server?

  • Can I approve commands from anywhere?

Yes! You can approve or deny requests from anywhere using WhatsApp.

  • What happens if I don't respond in time?

The approval request will expire after 5 minutes for security reasons.

  • Is there a way to track approval history?

Yes! The server maintains a database to track all approval requests.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
adstastic
Star
1
Language
Python
License
-

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)

a day ago