"MCP servers that use streamable HTTP as transport" matching MCP servers:

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.

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

A reference implementation for creating an MCP server supporting Streamable HTTP & SSE Transports with OAuth authorization, allowing developers to build OAuth-authorized MCP servers with minimal configuration.

Enables MCP-speaking clients to control a real desktop via the computer_use tool, including clicking, typing, scrolling, dragging, key combos, app focus, and screen/accessibility capture. It also provides a verdict system that verifies whether input actions had their intended effect, with configurable approval modes.

An open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.

MCP server for local Mac desktop control, enabling mouse, keyboard, and screenshot actions for AI agents like Grok and Cursor.

Enables an agent to see and operate a GNOME Wayland desktop like a human, including screenshots, mouse/keyboard control, accessibility tree access, OCR, clipboard, and audio listening.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

Enables Claude to see and control a real Android phone via MCP, reading the accessibility tree to tap, type, navigate, launch apps, and diagnose connectivity over ADB or cellular.

Exposes Anthropic's computer-use action surface (screenshot, click, move, keyboard, clipboard, batch) against a persistent desktop display via MCP stdio protocol. Enables AI agents to control a virtual desktop environment through natural language instructions.

Enables AI agents to operate local desktops and Chromium browsers through MCP tools, unifying accessibility trees, physical input, screenshots, DOM/ARIA, visual grounding, and result verification.

Enables AI agents to autonomously operate web browsers through the Model Context Protocol, including navigating pages, clicking, typing, filling forms, and extracting structured data.

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Enables MCP-capable agents to run TypeSafe's Jev judgment model as typed yes/no, choice, and score tools, with calibrated probabilities, confidence thresholds, escalation for uncertain or non-judgment tasks, and an optional action gate that fails open.

Enables localized macOS control by letting users grant temporary, window-scoped access for screen capture, pointer, keyboard, scrolling, clipboard, and Accessibility actions through a native host.

Enables LLMs to control Windows desktops via local OCR, optional YOLO icon detection, and mouse/keyboard actions.

Bridges Kimi Code CLI to OpenAI Computer Use, enabling Kimi to control local macOS applications via MCP.

Enables window management, screenshot, typing, and clicking on X11 with multi-monitor support.

A framework-agnostic computer-use MCP server that exposes core desktop operations (screen capture, mouse, keyboard, and file access) as standard MCP tools, enabling any MCP-compatible agent to drive a computer.

Enables Windows desktop automation via MCP, allowing AI agents to control mouse, keyboard, and screen capture with the same interface as Anthropic's computer-use tool.