"Marking Linux terminal commands as safe or unsafe for local execution" matching MCP servers:

Enables AI agents to interact with the Execute.run bot API for managing Shell balances, transferring funds, and executing LLM requests. It provides tools for identity verification, transaction tracking, and performing compute tasks through the Execute.run platform.

An MCP server that governs AI agent commands to physical robot arms, enforcing Asimov's Three Laws through Cedar authorization policies to prevent unsafe actions.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

Enables Codex to delegate review and implementation tasks to the local Qoder CN CLI as background jobs, with two permission tiers and polling-based status updates.

Exposes the local Claude Code CLI as a subagent for Codex, enabling background review and implementation jobs with two fixed permission tiers.

Delegates work from MCP clients (like Claude Code) to the Codex CLI, allowing spawning of autonomous Codex subagents for tasks.

Enables Claude Code and Codex to see and drive an X11 desktop through screenshots, mouse, keyboard, and accessibility-tree actions while keeping the user's own pointer and focus separate.

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

MCP server that verifies restaurant booking outcomes by reconciling API claims against independent re-reads, with a recovery dial for stakes-based retry policies.

Provides MCP tools for AI agents to classify changes into autonomous or human review lanes, and to run shadow simulations over backlogs without shipping anything.

Enables dispatching entire autonomous multi-agent engineering swarms directly from IDEs like Cursor and Windsurf via a single MCP endpoint, with streaming progress updates and verified git diffs returned to the editor.

Provides an AI agent with a fixed, isolated Linux desktop workspace, enabling bounded screen capture, input control, and application launching via MCP.

Enables an AI agent to see and control a Linux desktop via Wayland/Hyprland, providing screenshots, structured desktop state, pointer/keyboard input, semantic window/workspace tools, and a policy engine for safe execution.

Controls a real Linux desktop from any MCP host. Reads accessibility trees, takes screenshots, and drives clicks, scrolls, and keystrokes across GNOME, KDE/KWin, Hyprland, i3, and COSMIC.

A unified remote terminal management server that simplifies complex SSH connections and server management through MCP protocol, allowing users to control multiple remote servers with natural language commands as easily as local operations.

A runtime for inspectable agent workflows that provides MCP tools, bounded Python execution, session memory, and deterministic evaluation.

Enables efficient AI agent operations through sandboxed Python code execution with progressive tool discovery, PII tokenization, and skills persistence, achieving up to 98.7% token reduction by processing data in a sandbox rather than in context.

Enables any MCP client to execute DeepSeek Harness agents and shell commands through standard MCP tools, bridging multi-agent capabilities with sandboxed execution.

Provides safe Linux desktop automation for Codex through focused MCP tools for inspecting, clicking, typing, dragging, and verifying native applications on Wayland and X11.

A standalone MCP server for Linux desktop control, enabling screenshots, mouse/keyboard input, app/window management, and clipboard access via a Python bridge.