"filesystem" matching MCP servers:

A minimal MCP server that exposes three file operations (read_file, write_file, list_directory) within a sandboxed workspace, enabling file management via natural language.

Filesystem MCP server for AI assistants. Search, read, edit, and manage local files in directories you choose.

Enables reading, creating, and editing files on the local filesystem through operations like view, create, string replacement, and line insertion.

Enables reading, writing, appending, and listing files, restricted to explicitly allowed directories with safety checks against path traversal and symlink escapes.

Enables AI assistants to read, write, and manage files on the local system with security features like path restrictions and optional read-only mode.

A FastMCP server providing comprehensive file system, Docker, and Git operations with concurrency safety and dual transport support.

An enhanced Model Context Protocol filesystem server that fixes common limitations and adds features like glob pattern search, head/tail reading, intelligent file editing with syntax validation, and new tools for delete and command execution.

Provides intelligent file system operations with advanced features including code analysis and modification across multiple languages, version control (Git/GitHub), file compression, encryption, semantic search, batch operations, and secure shell command execution.

A secure, highly capable MCP server written in Rust. It exposes a comprehensive suite of filesystem operations as tools for AI agents.

Enables AI coding agents to watch directories for live filesystem changes (create, modify, delete, move) via the Model Context Protocol, providing event-driven access without busy-polling.

Node.js server implementing Model Context Protocol (MCP) for filesystem operations.

Exposes Linux filesystem operations as tools for LLM agents, with configurable root directory and read-only mode, built with FastMCP.

Enables reading, writing, editing, searching, and organizing files and directories within allowed root directories, with every tool result size-capped and large text files returned in paged windows instead of all at once. Media reads are rejected above a configurable byte limit, keeping responses bounded while preserving the usual filesystem tool set.

Enables advanced file system operations such as file read/write, directory management, search, archiving, and file watching through natural language.

A secure, read-only MCP server for browsing and searching files in a specified directory with path traversal protection and .gitignore support.

Provides local hybrid search over files by combining semantic vector and full-text BM25 retrieval, with MCP stdio/HTTP support, OAuth 2.1 authentication, and tools for reading and converting documents to Markdown.

Enables any MCP-compatible client to perform filesystem operations — reading, listing, writing, searching, watching directories, and batch processing files — over JSON-RPC 2.0 stdio transport. Includes resource discovery, metrics tracking, and security controls such as allowed roots, size limits, and format allowlists, with a LangGraph agent that accesses files exclusively through MCP.

High-performance MCP server giving AI agents advanced filesystem and automation capabilities on Windows, with 26 tools across file I/O, search, Git, process management, and more.

A completely stabilized filesystem MCP server optimized for Claude with overflow-proof design. Supports simultaneous multi-block editing with zero-failure guarantee, advanced error recovery, and performance-tuned parameters for maximum reliability.

Provides desktop AI clients with sandboxed, controlled read, write, search, and management access to user-selected local folders and projects over the Model Context Protocol.

A safe MCP server for sandboxed filesystem operations (list, move, create directories, delete files) via pure Python, designed for Claude Desktop.

A filesystem-based MCP server for AI coding agents to coordinate work across git worktrees by claiming files, checking for conflicts, and logging progress without affecting the repository's git history.

Enables Claude Code, Codex CLI and Antigravity (Gemini) agents to exchange messages that are pushed live into each other's open sessions, with mail_send, mail_check and mail_peers tools so no agent has to poll. Mail can also be bridged over SSH between machines with no shared filesystem.

SkillTotal is a local stdio MCP server that lets an agent check a component before installing it. It statically analyzes MCP servers, agent skills, npm/PyPI packages and repos for supply-chain risks, dangerous capabilities (shell, filesystem, network, credentials), prompt-injection surfaces like tool poisoning, and exfiltration paths. Each finding cites file, line and snippet.

Enables AI assistants to interact with local Obsidian vaults through direct filesystem access for reading, creating, and managing notes. It features high-performance SQLite indexing for fast searches, regex support, and tools for organizing tags and links without requiring additional plugins.

MCP server that vets LLM-emitted shell commands BEFORE execution — detects rm -rf nested deep in chains, package-manager glob removal (apt remove 'nvidia'), dd/mkfs filesystem destruction, chmod 777 / chown -R privilege blast, network-exfil via curl | bash, chained shutdown/reboot, git destructive ops. 30 detection rules across 8 families. Sub-second, local, free, MCP-native.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

A secure local MCP server that provides AI assistants controlled filesystem access and command execution with an interactive approval system for dangerous actions.

Serves an LLM-maintained markdown wiki to agents over MCP, providing tools for querying and navigating wiki pages without direct filesystem access.

Upload any file from the local filesystem and get a shareable, expiring link — with tools to check file status, list recent uploads, and delete files on demand.

An MCP server that provides AI agents with a persistent, PostgreSQL-backed virtual filesystem, supporting session-isolated file operations, cross-session shared stores, and glob/grep search.

Enables management of BTRFS snapshots via Snapper and monitoring of BTRFS filesystem health through the Model Context Protocol.

Enables local, event-driven messaging between multiple AI coding-agent sessions on the same machine using only Node.js and the filesystem, allowing them to hand off tasks, exchange replies, and broadcast announcements without external infrastructure.

Local inter-agent messaging for AI coding agents via filesystem relay.

Enables AI agents to interact with Kubernetes clusters through progressive disclosure, where agents discover TypeScript modules via filesystem, write and execute code, and receive summarized console output for cluster management tasks.

Enables AI coding agents to safely execute code, run tests, and build projects inside disposable Docker sandboxes, protecting the host machine through enforced isolation, filesystem snapshots, and network controls.

Provides AI agents with local-first access to Collibra developer documentation via MCP, combining deterministic filesystem search with semantic RAG retrieval.

Enables Cursor agents to read, write, search, and manage local Obsidian vaults via 13 tools with safe writes and direct filesystem access.

Lets a frontier coding agent delegate research, cataloguing, and long-running computation to a local LLM with guarded filesystem, web, and Python execution tools, preserving the agent's context and tokens.

An MCP memory server for coding agents that checks stored facts against the filesystem and git before relying on them, flagging stale memories.