How do I use claude-code-worker?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@claude-code-worker start a worker named alice to fix the login bug and wait for it to finish" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

claude-code-worker

by Rayudu0729

Overview Schema Source Related Servers Discussions Admin

JavaScript

Local

Claude Code Worker (cc-bridge)

Run the interactive claude CLI so that both you and a Claude desktop session can drive the same run. With the MCP server, a Claude Desktop (or Claude Code) session can start and drive CLI "worker" runs as a boss: hand out tasks, answer the workers' questions, and review their work at the end. Design: DESIGN.md. Plan: PLAN.md.

Install as a Claude Code plugin (`cli-workers`)

Windows (ConPTY), Node 24+, and the claude CLI on PATH.

claude plugin marketplace add Rayudu0729/claude-code-worker
claude plugin install cli-workers@cli-workers

Or inside a session: /plugin marketplace add Rayudu0729/claude-code-worker, then /plugin install cli-workers@cli-workers. Start a new session afterwards.

The plugin brings:

Part	What
MCP server `claude-code-worker`	the `cc_` tools below (`mcp__plugin_cli-workers_claude-code-worker__cc_`)
Skill `worker-boss`	the boss rules: delegate to workers, pick models, answer questions, review only at the end, run unattended
`/worker-run <task>`	hand a task to workers and run it unattended
`/workers [stop <name>\|stop all]`	list or stop workers
SessionStart hook	runs `npm ci` in the plugin folder on first use and after updates (the MCP launcher does the same if it starts first)

To use the tools without permission prompts, add "permissions": { "allow": ["mcp__plugin_cli-workers_claude-code-worker"] } to ~/.claude/settings.json.

Manual install (without the plugin system)

git clone https://github.com/Rayudu0729/claude-code-worker $HOME\.claude\tools\cc-bridge
cd $HOME\.claude\tools\cc-bridge
npm ci
node smoke.mjs
claude mcp add -s user claude-code-worker -- node $HOME\.claude\tools\cc-bridge\cc-mcp.mjs

The boss rules are then in skills/worker-boss/SKILL.md; copy them into ~/.claude/CLAUDE.md.

Related MCP server: pokeclaw

Start a run (in your terminal; uses your CLI account)

node $HOME\.claude\tools\cc-bridge\cc-bridge.mjs start <name>
node $HOME\.claude\tools\cc-bridge\cc-bridge.mjs start <name> -- claude "/review"

Type in it as usual. It ends when claude exits.

Control it (from the desktop session)

node $HOME\.claude\tools\cc-bridge\cc-ctl.mjs <command> <name> ...

Command	Does
`screen <name> [--scrollback N]`	print the visible screen
`send <name> "<text>" [--enter]`	type text, optionally submit
`key <name> <Enter\|Esc\|Tab\|ShiftTab\|Up\|Down\|Left\|Right\|Backspace\|CtrlC> [--repeat N]`	press a key
`wait <name> --idle <sec> \| --match <regex> [--timeout <sec>]`	block until quiet or matched, then print the screen (exit 2 on timeout)
`status <name>` / `stop <name>`	status JSON / Ctrl-C, then kill after 3 s

Exit 3 = not running. Control is on 127.0.0.1 only, with a per-run token in %LOCALAPPDATA%\cc-bridge\<name>.json (removed on exit).

MCP server (native tools for Claude Code / Desktop)

cc-mcp.mjs exposes the same controls as MCP tools, as the MCP server claude-code-worker. Through the plugin the tools appear as mcp__plugin_cli-workers_claude-code-worker__cc_*; with a manual install as mcp__claude-code-worker__cc_*, registered with:

claude mcp add -s user claude-code-worker -- node $HOME\.claude\tools\cc-bridge\cc-mcp.mjs

Tool	Does
`cc_start`	start a worker run: `name`, `cwd`, `model` (haiku/sonnet/opus), `permission_mode`, `autocompact` (default 400000 tokens), `args` (claude flags / first prompt), `visible` (new terminal window, default) or hidden. Workers always use the inline TUI (`--settings {"tui":"default"}`) so output has scrollback, and get a system-prompt note plus `CC_BRIDGE_WORKER` env so they don't follow the orchestrator rules in the global CLAUDE.md or start workers. The result shows the effective permission mode; `command` shows `<worker prompt>` instead of the prompt text
`cc_list`	live runs
`cc_screen` / `cc_status`	read screen (`since_send` = whole output since the last send, or `scrollback` lines) with a working/idle state / status
`cc_send`	type text, Enter by default — prompts and slash commands (`/model opus`, `/mcp`, `/compact`). Multi-line text goes as one bracketed paste and is submitted once
`cc_key`	press a key (ShiftTab cycles permission mode)
`cc_wait`	block until `done` (claude turn over: no "esc to interrupt", screen steady 2 s), `idle` seconds, or regex `match`; `since_send` returns the whole reply. Keep `timeout` ≤ 50 s
`cc_stop`	stop a run; returns once it is gone
`cc_cli`	`claude mcp …`, `claude plugin …`, `claude --version` (other subcommands refused)
`cc_settings_get` / `cc_settings_set`	read / set / delete a dotted key in user, project or local `settings.json`
`cc_permission`	add / remove an allow, deny or ask rule

Runs started by the MCP server drop the host session's CLAUDECODE, CLAUDE_CODE_*, CLAUDE_AGENT_SDK_*, ANTHROPIC_BASE_URL etc. so they behave like a run from your own shell; any of those you set in your Windows user or system environment are kept. Hidden runs log the terminal stream to %LOCALAPPDATA%\cc-bridge\<name>.log.

Test

node $HOME\.claude\tools\cc-bridge\smoke.mjs
node $HOME\.claude\tools\cc-bridge\mcp-smoke.mjs [--visible]

This server cannot be deployed

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Shellway AOAuth
com.getshellway
Work on your own computers from Claude or ChatGPT: run commands, edit and search files.
Command Line Developer Tools
201
SentinelX MCPOAuth
app.sentinelx
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Shell Access OS Automation
215
BCD — Bridge Control Delegate A
com.snack-wrap.bcd
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
File Systems Command Line Browser Automation
711
ShardfluxOAuth
dev.shardflux
Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.
Agent Orchestration Code Execution Command Line
1

Related MCP Servers

mcp-terminal-server
Shell Access Command Line
Unfathomable-siren38
F
license
Not graded
quality
C
maintenance
Enables running interactive terminals inside Claude Code and Claude Desktop, supporting multiple sessions for different tasks.
Updated 5 days ago (2026-10-14 07:17 UTC)
-
pokeclaw
Coding Agents Code Execution Command Line
madebydia
A
license
Not graded
quality
D
maintenance
Enables MCP clients to spawn and control Codex CLI and Claude Code sessions on the host machine, with session management and filesystem access.
Updated 4 months ago (2026-06-08 12:59 UTC)
4
MIT
Terminal MCP Server
Shell Access Command Line
jonrad
F
license
Not graded
quality
F
maintenance
Enables interactive terminal sessions within Claude Code and Desktop, allowing users and AI to execute commands and manage multiple tabs.
Updated 7 months ago (2026-03-15 21:42 UTC)
2
-
Claude Code MCP
Coding Agents Command Line
jawkjiang
A
license
A
quality
D
maintenance
Enables AI agents to interact programmatically with Claude Code CLI, managing sessions, streaming outputs, and handling permission requests.
Updated 9 months ago (2026-02-03 05:11 UTC)
7
7 npm
1
MIT

Claude Code Worker (cc-bridge)

Install as a Claude Code plugin (cli-workers)