Filesystem MCP Server

PassAudited by ClawScan on May 10, 2026.

Overview

The skill’s filesystem access is disclosed and purpose-aligned, but it is powerful and should be configured to narrow, user-approved directories.

This skill appears coherent and not malicious based on the provided artifacts, but it grants agents meaningful local file power. Install only from a verified upstream source, pin or review the package if possible, configure only the specific folders needed, and use read-only mode unless the agent truly needs to write, move, or delete files.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

An agent could change, move, or delete files inside the directories the user allows.

Why it was flagged

The skill intentionally exposes broad filesystem mutation and deletion tools. This is purpose-aligned, but high-impact if the user configures broad directories.

Skill content
Read, write, create, delete, move, search files and directories ... Full Access (default)
Recommendation

Configure the smallest necessary directories, prefer read-only mode when possible, and review destructive file changes before approving them.

What this means

A changed or compromised upstream npm package could affect the local filesystem server the user runs.

Why it was flagged

The skill instructs users to install or run an external npm package without a pinned version. This is normal for this integration style, but users rely on npm package provenance.

Skill content
npm install -g @modelcontextprotocol/server-filesystem ... "command": "npx", "args": ["-y", "@modelcontextprotocol/server-filesystem"
Recommendation

Verify the npm package source, consider pinning a known-good version, and install from the official project repository where possible.

What this means

If broad or sensitive folders are allowed, private files or credentials may be read by the agent during a task.

Why it was flagged

The documented search and read operations can surface secrets or private content from allowed local paths into the agent’s working context.

Skill content
Agent: "Search for files containing 'API_KEY'"
Recommendation

Do not allow home directories, credential stores, or secret-heavy folders unless necessary; use read-only access for inspection tasks and exclude sensitive paths.