"Read the Docs" matching MCP servers:

Exposes persistent, stateful remote Bash sessions to AI agents via SSH, enabling command execution with preserved working directory and environment.

Provides comprehensive PC control capabilities including file operations (read, write, edit, delete), directory management, file search, and shell command execution through the Model Context Protocol.

Enables an MCP client to observe and control a text-mode DOS system via a Python bridge, supporting keyboard input and screen capture.

Enables secure remote SSH command execution with strict read-only enforcement, allowing safe delegation of SSH access to Claude while preventing write operations. Supports connection pooling, command validation, and comprehensive logging for audit trails.

Enables SSH remote command execution on any host using the system ssh binary, supporting existing configurations like ssh-agent, ProxyCommand, and jump hosts.

Gives Notion Custom Agents real file tools and a real terminal over the Model Context Protocol, enabling them to read, edit, and run commands directly on the user's machine.

A desktop launcher and local MCP workspace server that enables ChatGPT and other MCP clients to securely read, edit, search, run commands, and show changes in selected local project folders.

A Model Context Protocol server that allows AI to run any Open Source tool via pkgx, enabling Claude to execute commands while maintaining read-only access to the filesystem.

Local MCP server enabling Codex and ChatGPT to read/write files, execute commands, manage processes, use Git, and inspect images on the user's machine with full privileges.

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.

MCP server for managing SSH connections to remote servers, providing host registry, session pool, and secure command execution with read-only protection.

A plugin for the Tabby terminal emulator that allows AI assistants to execute commands, manage SSH sessions, and read terminal buffers through the Model Context Protocol. It includes a pair programming mode with confirmation dialogs to ensure safe and controlled terminal automation.

Read-only systemd inspection for Claude on Linux — list units, status, journal, failed units, unit files.

A Python-based server that enables AI assistants to interact with an Unraid server through the official Unraid GraphQL API, providing read-only access to system information, Docker containers, VMs, storage, and more.

Enables AI assistants to interact with conda CLI commands through the Model Context Protocol, providing structured tools for built-in and plugin commands while enforcing configurable read-only, write, and exec policies.

A read-only MCP server for Kubernetes that allows querying cluster information and diagnosing issues through natural language interfaces like Claude.

A secure SSH-based MCP server for diagnosing remote servers. It allows AI agents to execute read-only commands and read files automatically, while requiring user confirmation for write operations.

The fastest, most capable filesystem MCP server built in Rust, giving AI agents superpowers to read, search, edit, and manage files and directories.

Serves a local dsh workspace as a protected Streamable HTTP MCP endpoint, letting authenticated web AI agents read, search, patch, inspect, and operate the project, with optional shell commands, LSP support, and public tunneling.

This MCP server is pre-implementation; it is intended to enable read-only agent interaction with Bitty debug and command protocols, with explicit fine-grained authorization.