Skip to main content

/

/

Stats

Actions

Tags

Stats

Actions

Tags

ClaudePluginHub

Community directory for discovering and installing Claude Code plugins.

Find plugins for your project

AI-powered recommendations based on your stack.

Product

Browse Plugins
Marketplaces
Pricing
About
Contact

Resources

Learning Center
Blog
Weekly Digest
Claude Code Docs
Plugin Guide
Plugin Reference
Plugin Marketplaces

Community

Browse on GitHub
Get Support

Legal

Terms of Service
Privacy Policy

Browse · Plugins · Top Plugins · Marketplaces · Components · Technologies · Skills · Agents · Commands · Hooks · MCP Servers · LSP Servers · Output Styles · Themes · Monitors

Categories · Productivity · Development · Testing · Deployment · Security · Documentation · Data · Utilities

© 2025 ClaudePluginHub

Community Maintained · Not affiliated with Anthropic

ClaudePluginHub

ClaudePluginHub

Tools Learn Pricing

Search everything...

Home
Skills
security-guardrails
filesystem-mcp-guardrails

Skill

filesystem-mcp-guardrails

From security-guardrails

Use when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.

Popularity

Parent stars

5

Parent forks

1

Shared by

2

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/security-guardrails:filesystem-mcp-guardrails

User invocable

Model invocable

Inline context

Default effort

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

This is a conceptual document for a Filesystem MCP server configuration. It is NOT a runnable configuration file. The earlier research used a Go-based filesystem MCP shape; this skill keeps only the safety model.

Supporting Files

references/path-boundary-checklist.md

SKILL.md

34 lines · ~415 tokens

Stats

LanguageTypeScript

Parent stars5

Parent forks1

MaintenanceExcellent

Last CommitMay 6, 2026

Actions

View Source View Plugin View on GitHub View README

Stats

LanguageTypeScript

Parent stars5

Parent forks1

MaintenanceExcellent

Last CommitMay 6, 2026

Actions

View Source View Plugin View on GitHub View README

Filesystem MCP Guardrails

Status

This is a conceptual document for a Filesystem MCP server configuration. It is NOT a runnable configuration file. The earlier research used a Go-based filesystem MCP shape; this skill keeps only the safety model.

Intent

When packaged as a true Agent Powerup, this will provide guidance on configuring and safely running local filesystem MCP servers.

When to use

Use when the agent needs structured, protocol-driven access to the local filesystem beyond its native capabilities, or when integrating external tools that require filesystem access via MCP.

Safety Constraints

MCP servers providing filesystem access MUST be strictly bounded to the intended project directory.
Avoid configuring MCP servers with root or wide-ranging access.
Always require user approval before starting a new MCP server.
Prefer read-only operations until write need is explicit.
Keep allowlists for roots and methods; avoid broad recursive delete/move surfaces.
Log configured roots without exposing sensitive path contents.

Required Shipping Work

Before this becomes a shipped MCP config:

Define target-specific config files for Codex, Claude Code, and generic MCP clients.
Add apx mcp check metadata and dry-run install behavior.
Validate path boundary behavior on Windows and POSIX.
Add tests for refusal of out-of-root paths and dangerous methods.

References

references/path-boundary-checklist.md

filesystem-mcp-guardrails | security-guardrails

$

npx claudepluginhub yeaight7/agent-powerups --plugin security-guardrails

Similar Skills

gateguard

216.8k

Blocks Edit/Write/Bash actions until Claude investigates importers, data schemas, and user instructions. Improves output quality by forcing concrete facts before edits.