innerVoice
Verified Safeby RichardDillman
Overview
Two-way communication bridge for AI models (like Claude) to interact with users via Telegram for notifications, questions, and commands.
Installation
pnpm devEnvironment Variables
- TELEGRAM_BOT_TOKEN
- TELEGRAM_CHAT_ID
- PORT
- HOST
- ENABLED
- TELEGRAM_BRIDGE_URL
Security Notes
The server uses environment variables for sensitive data like the Telegram bot token, which is good practice. The core bridge service binds to `localhost:3456` by default, limiting direct external network exposure. It leverages `child_process.spawn` to start Claude instances, which can carry risks if project environments (e.g., `.env` files within a project's directory) or Claude's command itself are untrusted, though this is a general risk of such an architecture rather than a direct vulnerability of the bridge's code. No direct `eval` or obfuscation detected. Overall, it appears reasonably secure for its intended local deployment model.
Similar Servers
zenfeed
An AI-powered information hub that acts as an intelligent RSS reader, real-time news knowledge base, and personal assistant for monitoring events and delivering analysis reports.
cupertino
Local Apple Developer documentation crawler and Model Context Protocol (MCP) server for AI agents, providing offline access and structured API information.
mcp-server-infranodus
Integrates InfraNodus knowledge graph and text network analysis capabilities into LLM workflows and AI assistants for advanced text analysis, content gap detection, and SEO optimization.
mcp-server-computer
This server acts as a Spring AI MCP Server component to provide cross-platform computer configuration information (OS, user, Java, and platform-specific details) to an AI agent.