1. Conduid
  2. Developer Tools
  3. Shellfirm
MCP server · Developer Tools

Shellfirm

Safety guardrails for ai coding agents and human terminal commands

87Excellent

Scored 7 hours ago · breakdown

About Shellfirm

Shellfirm is an MCP server published by kaplanelad in the Developer Tools category: safety guardrails for ai coding agents and human terminal commands.

The repository has 946 stars and 33 forks, with the last commit 5 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/kaplanelad/shellfirm

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (4)

check_commandCheck if a command is risky — returns severity, matched rules, and alternatives

Parameters not published.

explain_riskDetailed explanation of why a command is dangerous

Parameters not published.

get_policyRead the active shellfirm configuration and project policy

Parameters not published.

suggest_alternativeGet safer replacement commands

Parameters not published.

Ask AI

✦

Ask AI about Shellfirm

Powered by Claude · Grounded in docs

I know everything about Shellfirm. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 7 hours ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

v0.3.10v0.3.10 · 7 May 2026
v0.3.9v0.3.9 · 29 Mar 2026
v0.3.8v0.3.8 · 25 Mar 2026
v0.3.7v0.3.7 · 12 Mar 2026
v0.3.6v0.3.6 · 6 Mar 2026

README

shellfirm

Think before you execute.

Humans make mistakes. AI agents make them faster. shellfirm intercepts dangerous shell commands before the damage is done.

$ rm -rf ./src
============ RISKY COMMAND DETECTED ============
Severity: Critical
Blast radius: [PROJECT] — Deletes 347 files (12.4 MB) in ./src
Description: You are going to delete everything in the path.

Solve the challenge: 8 + 0 = ? (^C to cancel)
$ git push origin main --force
============ RISKY COMMAND DETECTED ============
Severity: High
Blast radius: [RESOURCE] — Force-pushes branch main (3 commits behind remote)
Description: This command will force push and overwrite remote history.
Alternative: git push --force-with-lease
  (Checks that your local ref is up-to-date before force pushing, preventing accidental overwrites of others' work.)

Solve the challenge: 3 + 5 = ? (^C to cancel)

Features

  • 100+ patterns across 9 ecosystems (filesystem, git, Kubernetes, Terraform, Docker, AWS, GCP/Azure, Heroku, databases)
  • 8 shells — Zsh, Bash, Fish, Nushell, PowerShell, Elvish, Xonsh, Oils
  • Context-aware escalation — harder challenges when connected via SSH, running as root, on protected git branches, or in production Kubernetes clusters
  • Safe alternative suggestions — actionable safer commands shown alongside every warning
  • Severity levels with configurable thresholds (Critical, High, Medium, Low, Info)
  • Project policies — share team safety rules via .shellfirm.yaml (additive-only, never weakens)
  • Audit trail — every intercepted command and decision logged as JSON-lines
  • Blast radius detection — runtime context signals feed into risk scoring
  • MCP server — expose shellfirm as an AI tool for Claude Code, Cursor, and other agents

AI Tool Integration

Claude Code

One command sets up both automatic safety (hooks) and on-demand analysis (MCP):

shellfirm connect claude-code

This adds:

  • Hooks — every Bash command is checked before execution; risky commands are blocked
  • MCP — Claude can call shellfirm tools to explain risks and suggest alternatives

MCP Tools

Tool Description
check_command Check if a command is risky — returns severity, matched rules, and alternatives
suggest_alternative Get safer replacement commands
explain_risk Detailed explanation of why a command is dangerous
get_policy Read the active shellfirm configuration and project policy

Installation

npm

npm install -g @shellfirm/cli

Homebrew

brew tap kaplanelad/tap && brew install shellfirm

Cargo

cargo install shellfirm

Or download the binary from the releases page.


Quick Start

1. Install the shell hook (auto-detects your shell):

shellfirm init

2. Restart your shell (or source your rc file).

3. Try it:

git reset --hard  # Should trigger shellfirm!

For manual setup, shell-specific instructions, and Oh My Zsh plugin, see the shell setup docs.


Documentation

Full documentation is available at shellfirm.vercel.app:


Contributing

Contributions are welcome! Please open an issue or pull request on GitHub.

License

Apache-2.0

README fetched from the repository 7 hours ago. The original is authoritative.

Questions

About Shellfirm

How do I install Shellfirm?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Shellfirm safe to use with an AI agent?

Its trust score is 87 out of 100 (excellent). It passes 5 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Shellfirm still maintained?

Yes — the latest release is v0.3.10 (7 May 2026), and the last commit was 5 months ago. The repository has 946 stars and 3 open issues.