Documentation 2026-03-20 21:05 UTC to 2026-03-21 18:03 UTC

12 12 

13A channel is an MCP server that pushes events into your running Claude Code session, so Claude can react to things that happen while you're not at the terminal. Channels can be two-way: Claude reads the event and replies back through the same channel, like a chat bridge. Events only arrive while the session is open, so for an always-on setup you run Claude in a background process or persistent terminal.13A channel is an MCP server that pushes events into your running Claude Code session, so Claude can react to things that happen while you're not at the terminal. Channels can be two-way: Claude reads the event and replies back through the same channel, like a chat bridge. Events only arrive while the session is open, so for an always-on setup you run Claude in a background process or persistent terminal.

14 14 

15Unlike integrations that spawn a fresh cloud session or wait to be polled, the event arrives in the session you already have open: see [how channels compare](#how-channels-compare).

16 

15You install a channel as a plugin and configure it with your own credentials. Telegram and Discord are included in the research preview.17You install a channel as a plugin and configure it with your own credentials. Telegram and Discord are included in the research preview.

16 18 

17When Claude replies through a channel, you see the inbound message in your terminal but not the reply text. The terminal shows the tool call and a confirmation (like "sent"), and the actual reply appears on the other platform.19When Claude replies through a channel, you see the inbound message in your terminal but not the reply text. The terminal shows the tool call and a confirmation (like "sent"), and the actual reply appears on the other platform.

22* [Install and run a channel](#quickstart) with fakechat, a localhost demo24* [Install and run a channel](#quickstart) with fakechat, a localhost demo

23* [Who can push messages](#security): sender allowlists and how you pair25* [Who can push messages](#security): sender allowlists and how you pair

24* [Enable channels for your organization](#enterprise-controls) on Team and Enterprise26* [Enable channels for your organization](#enterprise-controls) on Team and Enterprise

27* [How channels compare](#how-channels-compare) to web sessions, Slack, MCP, and Remote Control

25 28 

26To build your own channel, see the [Channels reference](/en/channels-reference).29To build your own channel, see the [Channels reference](/en/channels-reference).

27 30 

252 255 

253Report issues or feedback on the [Claude Code GitHub repository](https://github.com/anthropics/claude-code/issues).256Report issues or feedback on the [Claude Code GitHub repository](https://github.com/anthropics/claude-code/issues).

254 257 

258## How channels compare

259 

260Several Claude Code features connect to systems outside the terminal, each suited to a different kind of work:

261 

262| Feature | What it does | Good for |

263| ---------------------------------------------------- | --------------------------------------------------------------------- | --------------------------------------------------------- |

264| [Claude Code on the web](/en/claude-code-on-the-web) | Runs tasks in a fresh cloud sandbox, cloned from GitHub | Delegating self-contained async work you check on later |

265| [Claude in Slack](/en/slack) | Spawns a web session from an `@Claude` mention in a channel or thread | Starting tasks directly from team conversation context |

266| Standard [MCP server](/en/mcp) | Claude queries it during a task; nothing is pushed to the session | Giving Claude on-demand access to read or query a system |

267| [Remote Control](/en/remote-control) | You drive your local session from claude.ai or the Claude mobile app | Steering an in-progress session while away from your desk |

268 

269Channels fill the gap in that list by pushing events from non-Claude sources into your already-running local session.

270 

271* **Chat bridge**: ask Claude something from your phone via Telegram or Discord, and the answer comes back in the same chat while the work runs on your machine against your real files.

272* **[Webhook receiver](/en/channels-reference#example-build-a-webhook-receiver)**: a webhook from CI, your error tracker, a deploy pipeline, or other external service arrives where Claude already has your files open and remembers what you were debugging.

273 

255## Next steps274## Next steps

256 275 

257Once you have a channel running, explore these related features:276Once you have a channel running, explore these related features:

115 </Step>115 </Step>

116 116 

117 <Step title="Register your server with Claude Code">117 <Step title="Register your server with Claude Code">

118 Add the server to `.mcp.json` so Claude Code knows how to start it. If you're adding it to a project-level `.mcp.json` in the same directory, use a relative path. If you're adding it to your user-level `~/.mcp.json`, use the full absolute path:118 Add the server to your MCP config so Claude Code knows how to start it. For a project-level `.mcp.json` in the same directory, use a relative path. For user-level config in `~/.claude.json`, use the full absolute path so the server can be found from any project:

119 119 

120 ```json title=".mcp.json" theme={null}120 ```json title=".mcp.json" theme={null}

121 {121 {

125 }125 }

126 ```126 ```

127 127 

128 Claude Code reads `.mcp.json` at startup and spawns each server as a subprocess.128 Claude Code reads your MCP config at startup and spawns each server as a subprocess.

129 </Step>129 </Step>

130 130 

131 <Step title="Test it">131 <Step title="Test it">

135 claude --dangerously-load-development-channels server:webhook135 claude --dangerously-load-development-channels server:webhook

136 ```136 ```

137 137 

138 When Claude Code starts, it reads `.mcp.json`, spawns your `webhook.ts` as a subprocess, and the HTTP listener starts automatically on the port you configured (8788 in this example). You don't need to run the server yourself.138 When Claude Code starts, it reads your MCP config, spawns your `webhook.ts` as a subprocess, and the HTTP listener starts automatically on the port you configured (8788 in this example). You don't need to run the server yourself.

139 139 

140 If you see "blocked by org policy," your Team or Enterprise admin needs to [enable channels](/en/channels#enterprise-controls) first.140 If you see "blocked by org policy," your Team or Enterprise admin needs to [enable channels](/en/channels#enterprise-controls) first.

141 141 

428 428 

429These settings are configured through the [admin settings console](https://claude.ai/admin-settings/claude-code):429These settings are configured through the [admin settings console](https://claude.ai/admin-settings/claude-code):

430 430 

431* **Enable or disable the Code tab**: control whether users in your organization can access Claude Code in the desktop app431* **Code in the desktop**: control whether users in your organization can access Claude Code in the desktop app

432* **Code in the web**: enable or disable [web sessions](/en/claude-code-on-the-web) for your organization

433* **Remote Control**: enable or disable [Remote Control](/en/remote-control) for your organization

432* **Disable Bypass permissions mode**: prevent users in your organization from enabling bypass permissions mode434* **Disable Bypass permissions mode**: prevent users in your organization from enabling bypass permissions mode

433* **Disable Claude Code on the web**: enable or disable remote sessions for your organization

434 435 

435### Managed settings436### Managed settings

436 437 

58| `CLAUDE_CODE_EXIT_AFTER_STOP_DELAY` | Time in milliseconds to wait after the query loop becomes idle before automatically exiting. Useful for automated workflows and scripts using SDK mode |58| `CLAUDE_CODE_EXIT_AFTER_STOP_DELAY` | Time in milliseconds to wait after the query loop becomes idle before automatically exiting. Useful for automated workflows and scripts using SDK mode |

59| `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` | Set to `1` to enable [agent teams](/en/agent-teams). Agent teams are experimental and disabled by default |59| `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` | Set to `1` to enable [agent teams](/en/agent-teams). Agent teams are experimental and disabled by default |

60| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override the default token limit for file reads. Useful when you need to read larger files in full |60| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override the default token limit for file reads. Useful when you need to read larger files in full |

61| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip auto-installation of IDE extensions |61| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip auto-installation of IDE extensions. Equivalent to setting [`autoInstallIdeExtension`](/en/settings#global-config-settings) to `false` |

62| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Defaults and caps vary by model; see [max output tokens](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison). Increasing this value reduces the effective context window available before [auto-compaction](/en/costs#reduce-token-usage) triggers. |62| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Defaults and caps vary by model; see [max output tokens](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison). Increasing this value reduces the effective context window available before [auto-compaction](/en/costs#reduce-token-usage) triggers. |

63| `CLAUDE_CODE_NEW_INIT` | Set to `true` to make `/init` run an interactive setup flow. The flow asks which files to generate, including CLAUDE.md, skills, and hooks, before exploring the codebase and writing them. Without this variable, `/init` generates a CLAUDE.md automatically without prompting. |63| `CLAUDE_CODE_NEW_INIT` | Set to `true` to make `/init` run an interactive setup flow. The flow asks which files to generate, including CLAUDE.md, skills, and hooks, before exploring the codebase and writing them. Without this variable, `/init` generates a CLAUDE.md automatically without prompting. |

64| `CLAUDE_CODE_ORGANIZATION_UUID` | Organization UUID for the authenticated user. Used by SDK callers to provide account information synchronously. Requires `CLAUDE_CODE_ACCOUNT_UUID` and `CLAUDE_CODE_USER_EMAIL` to also be set |64| `CLAUDE_CODE_ORGANIZATION_UUID` | Organization UUID for the authenticated user. Used by SDK callers to provide account information synchronously. Requires `CLAUDE_CODE_ACCOUNT_UUID` and `CLAUDE_CODE_USER_EMAIL` to also be set |

650* `--max-turns`: Maximum conversation turns (default: 10)650* `--max-turns`: Maximum conversation turns (default: 10)

651* `--model`: Model to use (for example, `claude-sonnet-4-6`)651* `--model`: Model to use (for example, `claude-sonnet-4-6`)

652* `--mcp-config`: Path to MCP configuration652* `--mcp-config`: Path to MCP configuration

653* `--allowed-tools`: Comma-separated list of allowed tools653* `--allowedTools`: Comma-separated list of allowed tools. The `--allowed-tools` alias also works.

654* `--debug`: Enable debug output654* `--debug`: Enable debug output

655 655 

656### Alternative integration methods656### Alternative integration methods

30 30 

31Before using Remote Control, confirm that your environment meets these conditions:31Before using Remote Control, confirm that your environment meets these conditions:

32 32 

33* **Subscription**: available on Pro, Max, Team, and Enterprise plans. On Team and Enterprise, an admin must first enable the Remote Control toggle in [Claude Code admin settings](https://claude.ai/admin-settings/claude-code). API keys are not supported.33* **Subscription**: available on Pro, Max, Team, and Enterprise plans. API keys are not supported. On Team and Enterprise, an admin must first enable the Remote Control toggle in [Claude Code admin settings](https://claude.ai/admin-settings/claude-code).

34* **Authentication**: run `claude` and use `/login` to sign in through claude.ai if you haven't already.34* **Authentication**: run `claude` and use `/login` to sign in through claude.ai if you haven't already.

35* **Workspace trust**: run `claude` in your project directory at least once to accept the workspace trust dialog.35* **Workspace trust**: run `claude` in your project directory at least once to accept the workspace trust dialog.

36 36 

148 148 

149### "Remote Control is disabled by your organization's policy"149### "Remote Control is disabled by your organization's policy"

150 150 

151This error has three distinct causes. The first is the most common on developer machines.151This error has three distinct causes. Run `/status` first to see which login method and subscription you're using.

152 152 

153* **You're authenticated with an API key or Console account**: Remote Control requires claude.ai OAuth. Run `/login` and choose the claude.ai option. If `ANTHROPIC_API_KEY` is set in your environment, unset it.153* **You're authenticated with an API key or Console account**: Remote Control requires claude.ai OAuth. Run `/login` and choose the claude.ai option. If `ANTHROPIC_API_KEY` is set in your environment, unset it.

154* **Your Team or Enterprise admin hasn't enabled it**: Remote Control is off by default on these plans. An admin can turn it on at [claude.ai/admin-settings/claude-code](https://claude.ai/admin-settings/claude-code). The Remote Control toggle depends on the Claude Code on the web toggle on the same page; enable Claude Code on the web first if Remote Control appears unavailable.154* **Your Team or Enterprise admin hasn't enabled it**: Remote Control is off by default on these plans. An admin can enable it at [claude.ai/admin-settings/claude-code](https://claude.ai/admin-settings/claude-code) by turning on the **Remote Control** toggle. This is a server-side organization setting, not a [managed settings](/en/permissions#managed-only-settings) key.

155* **The admin toggle is grayed out**: your organization has a data retention or compliance configuration that is incompatible with Remote Control. This cannot be changed from the admin panel. Contact Anthropic support to discuss options.155* **The admin toggle is grayed out**: your organization has a data retention or compliance configuration that is incompatible with Remote Control. This cannot be changed from the admin panel. Contact Anthropic support to discuss options.

156 156 

157### "Remote credentials fetch failed"157### "Remote credentials fetch failed"

202 202 

203### Global config settings203### Global config settings

204 204 

205These display preferences are stored in `~/.claude.json` rather than `settings.json`. Adding them to `settings.json` will trigger a schema validation error.205These settings are stored in `~/.claude.json` rather than `settings.json`. Adding them to `settings.json` will trigger a schema validation error.

206 206 

207| Key | Description | Example |207| Key | Description | Example |

208| :--------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :------ |208| :--------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------ |

209| `autoConnectIde` | Automatically connect to a running IDE when Claude Code starts from an external terminal. Default: `false`. Appears in `/config` as **Auto-connect to IDE (external terminal)** when running outside a VS Code or JetBrains terminal | `true` |

210| `autoInstallIdeExtension` | Automatically install the Claude Code IDE extension when running from a VS Code terminal. Default: `true`. Appears in `/config` as **Auto-install IDE extension** when running inside a VS Code or JetBrains terminal. You can also set the [`CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL`](/en/env-vars) environment variable | `false` |

209| `showTurnDuration` | Show turn duration messages after responses, e.g. "Cooked for 1m 6s". Default: `true`. Appears in `/config` as **Show turn duration** | `false` |211| `showTurnDuration` | Show turn duration messages after responses, e.g. "Cooked for 1m 6s". Default: `true`. Appears in `/config` as **Show turn duration** | `false` |

210| `terminalProgressBarEnabled` | Show the terminal progress bar in supported terminals like Windows Terminal and iTerm2. Default: `true`. Appears in `/config` as **Terminal progress bar** | `false` |212| `terminalProgressBarEnabled` | Show the terminal progress bar in supported terminals like Windows Terminal and iTerm2. Default: `true`. Appears in `/config` as **Terminal progress bar** | `false` |

211 213