# Filesystem

> Use this tool when you need to securely access and manage local filesystems with advanced capabilities, such as line-targeted reading and editing, powerful search, and intelligent context management. It solves problems related to navigating and manipulating large codebases or text datasets, providing precise control while maintaining strict path validation for security. The Filesystem tool accepts file paths and commands as inputs and returns file contents, search results, or operation outcomes as outputs.

Canonical page: https://skillsregistry.net/skills/safurrier-filesystem  
JSON: https://api.skillsregistry.net/v1/skills/safurrier-filesystem

## Description

MCP-Filesystem provides secure, token-efficient access to local filesystems with advanced capabilities beyond basic file operations. Built by Alex Furrier, it features line-targeted reading and editing with content verification, powerful search through ripgrep integration, and intelligent context management for large files. The implementation includes pagination controls to prevent context overflow, multi-file operations to reduce round-trips, and specialized utilities like file comparison and directory analysis. This server is particularly valuable for AI assistants working with large codebases or text datasets, enabling precise navigation and manipulation while maintaining strict path validation for security.

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/safurrier-filesystem)
- **Repository:** <https://github.com/safurrier/mcp-filesystem>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "safurrier-filesystem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/safurrier-filesystem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/safurrier-filesystem/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt