Enterprise DNA
M MCP Servers Developer low

j0hanz/filesystem-context-mcp-server

by Various

A local filesystem MCP server that lets LLMs and AI agents read, write, search, diff, patch, and manage files safely and efficiently. Built for reliable, structured, and controlled

J

MCP

j0hanz/filesystem-context-mcp-server

Added 1 June 2026

#analysis #diff #exploitation #file-management #file-operations #filesystem #glob #grep

Overview

A local filesystem MCP server that exposes file read, write, search, diff, patch, and management operations to LLMs and AI agents. It runs as a process on the user's machine, providing structured and controlled filesystem access through the Model Context Protocol.

Best for

Best for
Developers who need to give LLM-based agents safe, structured access to local file systems

Use cases

  • Enabling an LLM agent to edit code files in a local project
  • Allowing a chat assistant to read and summarize files from disk
  • Letting an AI tool perform safe file patching and diff operations

How to use

Install

code --add-mcp '{"name":"filesystem","command":"npx","args":["-y","@j0hanz/filesystem-mcp@latest"]}'

Tools exposed

  • get-help
  • compare-files
  • analyze-path
  • get-tool-help
  • FILESYSTEM_MCP_API_KEY
  • FILESYSTEM_MCP_MAX_HTTP_SESSIONS
  • FILESYSTEM_MCP_HTTP_HOST
  • FS_CONTEXT_MAX_REQUEST_BYTES
  • MAX_FILE_SIZE
  • MAX_SEARCH_SIZE
  • MAX_READ_MANY_TOTAL_SIZE
  • DEFAULT_SEARCH_TIMEOUT
  • FS_CONTEXT_ALLOW_SENSITIVE
  • FS_CONTEXT_DENYLIST
  • FS_CONTEXT_ALLOWLIST
  • FS_CONTEXT_MAX_INLINE_CHARS
  • FS_CONTEXT_MAX_INLINE_MATCHES
  • FS_CONTEXT_STRIP_STRUCTURED
  • FILESYSTEM_MCP_MAX_TASK_TTL_MS
  • FILESYSTEM_MCP_MAX_CONCURRENT_TASKS

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf, Cline, VS Code

Example client config

{\n  "mcpServers": {\n    "filesystem": {\n      "command": "npx",\n      "args": ["-y", "@j0hanz/filesystem-mcp@latest"]\n    }\n  }\n}

Notes

A local filesystem MCP server that exposes file read, write, search, diff, patch, and management operations to LLMs and AI agents. It runs as a process on the user’s machine, providing structured and controlled filesystem access through the Model Context Protocol.

8 stars on GitHub. Last updated 2026-06-01. Licensed MIT.

Use cases

  • Enabling an LLM agent to edit code files in a local project
  • Allowing a chat assistant to read and summarize files from disk
  • Letting an AI tool perform safe file patching and diff operations

Pros

  • Runs locally so files never leave the user’s machine
  • Provides fine-grained file operations (read, write, diff, patch, search)
  • Built with TypeScript for reliability and type safety

Cons

  • Very low community adoption with only 8 GitHub stars
  • Requires manual setup and running a dedicated server process
  • Limited to local filesystem interactions only

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Runs locally so files never leave the user's machine
  • Provides fine-grained file operations (read, write, diff, patch, search)
  • Built with TypeScript for reliability and type safety

Cons

  • Very low community adoption with only 8 GitHub stars
  • Requires manual setup and running a dedicated server process
  • Limited to local filesystem interactions only
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks