"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.

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

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

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.

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

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.

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.

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

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.

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

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

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.

Enables natural-language diagnosis of Linux system issues by providing sandboxed, typed tools for system, service, filesystem, and git inspection, with human approval for mutating actions.

Enables local stdio-based interaction with SingleStore databases from MCP clients, letting users run SQL, inspect schemas, and manage SingleStore Pipelines for continuous data loading from S3, Kafka, Azure, GCS, or filesystem sources.

Enables interaction with multiple Obsidian vaults through natural language, supporting note operations, search, and vault management with both REST and filesystem backends.

Enables MCP-compatible assistants to lint, format, render, parse, and migrate Carve documents directly from source text, without filesystem or network access.

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.