# Filesystem

> Use this tool when you need to securely interact with local filesystems, manage files and directories with granular permissions, and perform operations like reading, writing, and searching while enforcing system security. It solves problems related to code manipulation, configuration management, and data analysis by providing a controlled environment for AI assistants to access and modify files. The Filesystem tool accepts inputs like file paths and operation requests, and outputs results like file contents or success/failure status, making it ideal for use cases requiring secure file system access and management.

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

## Description

Filesystem MCP Server provides secure, permission-controlled access to local filesystems through a comprehensive set of tools for file and directory operations. Built with TypeScript and Node.js, it implements granular permission controls (read-only, full access, or operation-specific permissions), path validation to prevent directory traversal, and specialized handlers for XML/JSON processing. The server supports common operations like reading, writing, moving, and searching files, while enforcing security through allowed directory restrictions and optional symlink controls. It's particularly valuable for AI assistants that need to safely interact with file systems for tasks like code manipulation, configuration management, or data analysis without compromising system security.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mateicanavra-filesystem)
- **Repository:** <https://github.com/rawr-ai/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": "mateicanavra-filesystem"
    }
  }
}
```

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