Claude Code Channels let you control your local coding session from anywhere. Using MCP servers, you can bridge Claude to Telegram and Discord to push events, receive alerts, and reply to your terminal assistant directly from your phone.
The new Channels support for Claude Code is a massive workflow upgrade, especially if you run long or complex tasks.
Instead of being tethered to your terminal waiting for Claude to finish a heavy refactor or CI pipeline, you can now bridge the session directly to Telegram or Discord via MCP servers. It’s a true two-way street: you can push events into the running session, and Claude can send progress updates, ask for permission approvals, or deliver the final results right to your phone.
The setup process is very straightforward. You just install the official plugins, drop in your bot token, pair it via a DM code, and lock down the allowlist.
this is actually a workflow gap I run into a lot - Claude Code does the work but then you want to push updates or get notified without staring at a terminal. how does the Telegram/Discord integration handle long-running tasks? like if a coding session takes 10 minutes, does it stream progress or just send a completion event?
Report
I've been using Claude for parsing messy legacy codebases - it's surprisingly good at understanding the intent behind uncommented functions written by developers who apparently believed variable names were a luxury. The constitutional AI approach means it won't just blindly refactor everything into unreadable one-liners like some other models I've tried.
Report
I didn't successfully got it working with telegram channel. Not with paring code or user id. No response in telegram
Report
Finally figured out that it require that I have bun installed. `brew install oven-sh/bun/bun`
Report
@lajlev thanks for the insights…, run into the same issues to, but now fixed and it’s just great!
Report
trying hard to clone Openclaw it they got acquihired by ClosedAI :p
Report
notifications are the easy part tbh. the real problem is knowing when the agent should ask you vs just do the thing. most of these integrations are basically glorified webhooks rn, not actual two-way control. ive been running coding agents that message me on whatsapp when they need a decision and honestly 90% of the time i just say "yes do it" which means the agent shouldve just done it without asking
Report
The Telegram/Discord bridge is what I've been wanting forever. Right now when I kick off a long refactor with Claude Code I literally can't close my laptop or I lose the session. Being able to get a ping on my phone when it needs permission or hits an error is huge.
How does it handle the permission approval flow through Telegram? Like if Claude wants to run a destructive command, can you approve/deny from the chat?
Replies
Flowtica Scribe
Hi everyone!
The new Channels support for Claude Code is a massive workflow upgrade, especially if you run long or complex tasks.
Instead of being tethered to your terminal waiting for Claude to finish a heavy refactor or CI pipeline, you can now bridge the session directly to Telegram or Discord via MCP servers. It’s a true two-way street: you can push events into the running session, and Claude can send progress updates, ask for permission approvals, or deliver the final results right to your phone.
The setup process is very straightforward. You just install the official plugins, drop in your bot token, pair it via a DM code, and lock down the allowlist.
This might put a little pressure on @OpenClaw :)
this is actually a workflow gap I run into a lot - Claude Code does the work but then you want to push updates or get notified without staring at a terminal. how does the Telegram/Discord integration handle long-running tasks? like if a coding session takes 10 minutes, does it stream progress or just send a completion event?
I've been using Claude for parsing messy legacy codebases - it's surprisingly good at understanding the intent behind uncommented functions written by developers who apparently believed variable names were a luxury. The constitutional AI approach means it won't just blindly refactor everything into unreadable one-liners like some other models I've tried.
I didn't successfully got it working with telegram channel. Not with paring code or user id. No response in telegram
Finally figured out that it require that I have bun installed. `brew install oven-sh/bun/bun`
trying hard to clone Openclaw it they got acquihired by ClosedAI :p
notifications are the easy part tbh. the real problem is knowing when the agent should ask you vs just do the thing. most of these integrations are basically glorified webhooks rn, not actual two-way control. ive been running coding agents that message me on whatsapp when they need a decision and honestly 90% of the time i just say "yes do it" which means the agent shouldve just done it without asking
The Telegram/Discord bridge is what I've been wanting forever. Right now when I kick off a long refactor with Claude Code I literally can't close my laptop or I lose the session. Being able to get a ping on my phone when it needs permission or hits an error is huge.
How does it handle the permission approval flow through Telegram? Like if Claude wants to run a destructive command, can you approve/deny from the chat?