claude-wrap-mcp

An MCP server that lets an agent spawn and drive real Claude Code sessions, so Claude Code can run a fleet of Claude Code sub-agents. Built on claude-wrap.

Needs Node ≥ 18 and the claude CLI on your PATH. Headless sessions work everywhere; attaching to visible terminal windows is Windows-first.

Install

Terminal

npm install -g claude-wrap-mcp
claude mcp add claude-wrap -- claude-wrap-mcp

Or in .mcp.json / claude_desktop_config.json:

config.json

{
  "mcpServers": {
    "claude-wrap": { "command": "npx", "args": ["-y", "claude-wrap-mcp"] }
  }
}

Tools

Tool	What it does
`claude_spawn`	Start a session in an absolute `cwd`. Returns a `sessionId`.
`claude_ask`	Send a prompt, wait for idle, return the transcript tail + parsed state.
`claude_send`	Send raw input (`text` / `line` / `key`) without waiting — for long tasks.
`claude_status`	Busy, mode, tokens, pending permission prompt, todos, last 5 tool names.
`claude_tool_calls`	Page through the session's tool calls. Ids + names by default.
`claude_tool_result`	One tool call by id: its args and result.
`claude_snapshot`	The rendered transcript lines.
`claude_list`	Every session — spawned here or discovered.
`claude_resolve_permission`	`approve` / `deny` a pending permission prompt.
`claude_stop`	Shut down a session this server spawned.

There is a second family, claudep_*, that drives non-interactive claude -p sessions and returns structured JSON, tool calls, usage and cost.

Two things worth knowing:

Permission prompts are surfaced, not bypassed. When claude_ask or claude_status reports a permissionPrompt, answer it with claude_resolve_permission.
Tool calls are paged, not dumped. A status poll stays cheap because it carries only names; claude_tool_calls lists the rest and claude_tool_result fetches one call's output by id.

Develop

pnpm install
pnpm --filter claude-wrap-mcp build
pnpm --filter claude-wrap-mcp test

Claude Wrap MCP README

claude-wrap-mcp

Install

Tools

Develop

License