"filesystem" matching MCP servers:

A filesystem MCP server that preserves file inode and metadata when writing or editing files, operating within allowed directories.

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

MCP server for performing filesystem operations, enabling file management and manipulation through natural language.

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

Provides a hardened filesystem interface that lets a local model read and write files only within user-specified directories, with symlink protection and atomic operations.

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

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 exploration and search of local filesystems using glob pattern matching to find files and grep to search for text patterns within files.

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.

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.

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

MCP server that exposes agent-memory-daemon to any MCP-compatible client — Kiro (CLI & IDE), Claude Desktop, Cursor, and others. The daemon does the thinking (consolidation + extraction); this server is a thin filesystem bridge so agents can read, append, and search memory through the Model Context Protocol.

MCP server that gives Claude Desktop and other desktop MCP clients filesystem powers—read, write, edit, and manage files like AI coding assistants.

Provides transactional intelligence for AI agents, enabling safe tool execution with pre-flight invariant checks, sub-second filesystem snapshots/rollback, causal tracing, belief contradiction detection, and 15 native MCP tools for Claude Code.

MCP server that lets agents edit real Microsoft Word (.docx) documents - tracked changes, tables, styles, comments, content controls, and document properties - with every edit validated and previewed before saving. Built on the Open XML SDK (no Word automation); reads and writes documents in place through filesystem or SharePoint storage.

Enables executing local commands via an argv-based tool with optional non-interactive sudo, command allowlisting, and filesystem write confinement using Bubblewrap.

An all-in-one self-hosted remote MCP server and gateway that lets AI clients access filesystem, terminal, background processes, and computer-use tools, and multiplex local stdio MCP servers over Streamable HTTP on Linux, Jetson, macOS, and Windows. It bundles revocable API keys, OAuth 2.0, and a read-only/coding safety switch so cloud and desktop assistants can safely drive remote machines.

Enables AI agents to understand, inspect, create, validate, build, and document Jekyll component frameworks through Jekyll-aware tools, resources, prompts, sandboxed filesystem access, and configurable write modes.

Enables safe filesystem and git operations confined within a single allowed directory tree, using symlink-resolved path containment to protect against path traversal. Users can read, write, list, and search files, as well as initialize repos and run status, stage, commit, diff, and log operations through MCP.

AI agent file editing via MCP: JSON/YAML/TOML, AST renames, markdown, batch.

Comprehensive MCP server for filesystem operations, process management, interactive sessions, and async file search. Includes utilities for JSON repair, encoding fixes, duplicate detection, OCR, ZIP archives, and Markdown export.

A production-grade MCP server for Windows developer environments, providing AI assistants with secure terminal, filesystem, git, Docker, SQLite, browser, and GitHub capabilities through 12 providers and 40+ tools.

An MCP server for reading files from the local filesystem. Currently supports listing files in directories on the Desktop.

Enables LLM agents to search, inspect, inscribe, hone, and maintain a versioned library of learned procedures stored as Git-committed SKILL.md files with SQLite metadata and filesystem content. It also supports dropping observation notes, managing drafts, scouting external skills, and running catalogue health passes through intent-shaped tools that return structured results with next-step hints.

A proof-of-concept MCP server that scopes GitHub tools to the current repository without filesystem access, using MCP roots to carry the repo identity.

Enables read-only, allowlisted filesystem and Git inspection of explicitly configured local repositories through MCP, with bounded reads and no arbitrary path or write access.

Local macOS MCP bridge that gives ChatGPT shell, unrestricted filesystem access, real PTY sessions, background jobs, and read-only stored Codex history. ChatGPT stays the reasoning layer; the bridge makes no model calls.

Enables an MCP client to start and drive terminal processes, read and write files, make exact-match text edits, move files, inspect metadata, and paginate through local file-content searches. It also exposes configuration, prompt, usage and recent-call tools alongside those filesystem, search and process capabilities.

Provides read-only Model Context Protocol tools for My AskAI, enabling documentation search, filesystem queries, and pricing estimates.

Enables a remote MCP client to access narrowly scoped local filesystem resources and process capabilities through a loopback-only bridge. Supports guarded file reads, searches, and mutations, authenticated transport, and private reachability via OpenAI Secure MCP Tunnel.

MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.

Provides an MCP stdio interface for filesystem and volume analytics, including directory listings, cryptographic hashing, regex search, recursive disk usage, large-file and duplicate detection, and binary string extraction.

A Filesystem MCP server that allows an LLM to read and list files from a specified directory on your local machine through the Model Context Protocol.