Claude Wrap MCP server

by Alex-Kaff·io.github.Alex-Kaff/claude-wrap-mcp·v0.1.0

No reviews yet

MCP server that spawns and drives Claude Code sessions via claude-wrap.

A92/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A92/100

full report

Adoption

New

0 stars

Reviews

Write one

Nobody has reviewed Claude Wrap yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Claude Wrap tools (8, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

claude_askwrite action
Send a prompt to a session and wait until Claude goes idle. Returns the rendered transcript tail plus parsed state. If the timeout elapses while Claude is still working, returns status "busy" (not an error) \u2014 poll with claude_status or read claude_snapshot. The result may include a pending permissionPrompt; resolve it with claude_resolve_permission.
claude_list
List all sessions: in-process ones this server spawned and external instances discovered in the registry.
claude_resolve_permission
Resolve a pending permission prompt in a session. Use claude_status or claude_ask first to see whether a prompt is pending and what it asks.
claude_sendwrite action
Send raw input to a session and return immediately (do not wait for idle). Provide exactly one of: text (raw, no newline), line (text + Enter), or key (a named key such as enter, esc, up, down, tab, ctrl-c). Use this for long-running tasks, then poll with claude_status.
claude_snapshot
Return the rendered transcript lines for a session (the tail, cleaned of trailing blanks).
claude_spawn
Start a new headless Claude Code session in a working directory. Returns a sessionId used by the other claude_* tools. The `claude` CLI must be on PATH.
claude_status
Return the parsed state of a session: busy flag, mode, token count, any pending permission prompt, todo list, and visible tool calls.
claude_stop
Shut down an in-process session this server spawned. External instances are not stopped (close their window manually).

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan6 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 20 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Claude Wrap compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 92/100; higher than 95% of 48,255 servers
Tools: 8; the typical server has 7
Tools that change things: 25%; typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 6 read · 2 change

Install Claude Wrap in Claude Code, Cursor or VS Code

Runs npx -y claude-wrap-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add claude-wrap-mcp -- npx -y claude-wrap-mcp

Add to Cursor

What the publisher says

From the Claude Wrap repository's README, as published. We do not edit it. Read it on GitHub

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

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

Or in .mcp.json / claudedesktopconfig.json:

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

Tools

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:

claudestatus reports a permissionPrompt, answer it with clauderesolve_permission.

Permission prompts are surfaced, not bypassed. When claude_ask or

carries only names; claudetoolcalls lists the rest and claudetoolresult fetches one call's output by id.

Tool calls are paged, not dumped. A status poll stays cheap because it

Develop

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

License

Nothing above is checked by us. What we check is on the safety report.

Claude Wrap: common questions

Is Claude Wrap MCP server safe?: Yes, by our scan: it is graded A (92/100). Read the Claude Wrap safety report
How do I install Claude Wrap?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Claude Wrap need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Claude Wrap maintained?: The last commit was 58 days ago (2026-09-07). The latest release is v0.1.0.
How does Claude Wrap compare with other MCP servers?: safety score 92/100 (higher than 95% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.