Claude Code Channels

A mechanism for pushing events from third-party chat apps (iMessage, Telegram, Discord) or custom servers into a running Claude Code session. Each channel is an MCP server plus a plugin. The host machine runs Claude Code listening for channel messages, and external messages are injected into the session as if the user had typed them locally. Requires Mac OS for iMessage and full-disk access, plus enterprise admin approval on team plans.

Key points

  • Channels are MCP servers that push events into a live Claude Code session
  • Supported channels at launch: iMessage (Mac OS only), Telegram, Discord
  • Setup: install plugin via /plugins, grant full disk access, launch Claude with channel enabled
  • iMessage requires Mac OS host because it uses the native Messages database
  • Enterprise and team plans must enable channels in admin settings
  • Session must stay running locally — terminal close kills the channel
  • Different from Dispatch (message-triggered) and Remote Control (mobile steering of an active session)

Related entities

Related concepts

Source references

  • [src-004] Nate Herk cluster — Nate Herk — Claude Code cluster (21 videos)

– Videos referenced: hHlpVeooPrI, EqhKw0Oro_k

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 491 indexed pages and articles.

  1. Wiki concept Hermes Agent An open-source personal AI agent work surface from Nous Research that Nate Herk uses for general knowledge work, scheduled automations, and Related by telegram
  2. Wiki concept Mobile Agent Work Surface A mobile agent work surface is the pattern of using a phone-first chat interface, such as Telegram, as a low-friction front door Related by claude
  3. Insight AI Beyond POCs How enterprise AI moves beyond proofs of concept through ownership, governance, measurement, adoption, and production operating models Readers have engaged with this next