shelltools

shelltools is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from getholly/holly. Its token cost is not measured, scanned A, original, Apache-2.0.

A local MCP server that gives an AI coding assistant access to shell tools. It is started with the uv Python package runner from a configured project directory.

In plain words
What is it for?
It is for connecting shell tools to an AI coding assistant in the Holly setup. The input does not specify which shell actions are available.
Why use it?
It can provide shell-related actions through one configured server, so the assistant does not need each action set up separately.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

One of 3 entries in claude_desktop_config.json — they are configured in one file and arrive together.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/getholly/holly/claude-shelltools
Clone the repo
git clone --depth 1 https://github.com/getholly/holly

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

shelltools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

hilly/data/Claude/claude_desktop_config.json · 11 lines

What it actually says

{
  "shelltools": {
    "command": "uv",
    "args": [
      "--directory",
      "/home/kasm-user/workarea/techarge-projects/aiagents/",
      "run",
      "mcp_server.py"
    ]
  }
}
Same file

What else claude_desktop_config.json configures

This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 11 lines scan A e6ea7439009d

Subscribe to this mod's changes

shelltools is an MCP server published in the GitHub repository getholly/holly (23 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.