# Filesystem MCP

> Use this tool when you need to enable large language models (LLMs) to interact with the local filesystem, allowing them to read and write files, and perform file system operations. It solves problems such as data ingestion, file processing, and output generation, providing a seamless interface between LLMs and the local file system. The Filesystem MCP takes file paths and commands as inputs and returns file contents or operation results as outputs.

Canonical page: https://skillsregistry.net/skills/io-github-j0hanz-filesystem-mcp  
JSON: https://api.skillsregistry.net/v1/skills/io-github-j0hanz-filesystem-mcp

## Description

MCP Server that enables LLMs to interact with the local filesystem.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.j0hanz%2Ffilesystem-mcp)
- **Repository:** <https://github.com/j0hanz/filesystem-mcp>

## 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": "io-github-j0hanz-filesystem-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-j0hanz-filesystem-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-j0hanz-filesystem-mcp/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