"Understanding How to Use a Browser" matching MCP servers:

MCP server that gives any LLM a managed Docker workspace with live browser, terminal, code execution, document skills, and autonomous sub-agents.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables an MCP-compatible AI client to author Blender Python, run Blender, import the resulting asset into Unity with materials and a prefab, place it in the active scene, verify the import, and revise the same asset using stable IDs.

A runtime-free MCP server that converts source code into AST🌲, regardless of language.

Exposes OpenAI's signed Windows Computer Use runtime as an MCP server so an MCP client's agent can inspect and control native Windows applications through JavaScript calls, without a nested model. It supports app and window discovery, screenshots, accessibility text, clicking, typing, scrolling, dragging, and other UI automation actions.

A Model Context Protocol server that enables LLMs to interact with VS Code's Simple Browser, allowing for browser control, JavaScript execution, console monitoring, and navigation through natural language.

Connects ChatGPT to Roblox Studio's built-in MCP, enabling natural-language reading and writing of game data, including executing Luau code and modifying scripts and instances.

A Model Context Protocol (MCP) server that converts LaTeX mathematical expressions to MathML format.

Give your AI app any GitHub link and the job you want done. UGT gets the project running on your computer and hands you the result.

Enables AI-powered video creation by writing React/Remotion code, compiling it in real-time, and rendering the result as a live video inline in the chat.

Exposes the Grok Build CLI as MCP tools for Claude Code and other clients, enabling headless AI agents to perform tasks like code reviews, web research, and file operations with configurable permission levels.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

Enables AI assistants to write and execute C# code directly inside Autodesk Civil 3D, providing full API access through code generation and execution.

Gives AI coding agents typed, mode-gated access to a real WordPress site — content, media, users and settings via core REST, plus PHP execution, SQL queries, filesystem operations and Elementor page read/build/patch/snapshot via a companion bridge plugin. Destructive actions and code execution are guarded by feature flags, explicit confirm literals, dry runs, redaction and audit logging.

Bridges Claude Desktop with Claude Code CLI to delegate complex coding tasks like creating React apps, building APIs, and debugging scripts while maintaining interaction through the Desktop interface.

Converts Figma designs to React Native components, allowing users to extract components from Figma designs and generate corresponding React Native components with proper typing and styling.

A simple MCP server implementation in TypeScript that communicates over stdio, allowing users to ask questions that end with 'yes or no' to trigger the MCP tool in Cursor.

Enables AI assistants to create isolated Kubernetes Pod sessions for real-time shell command execution, file management, and Node.js code execution, with automatic TTL-based cleanup.

Enables MCP clients such as Claude Desktop or Cursor to inspect a coffee-shop sales database schema, validate SQL, and run guarded read-only queries. It supports natural-language questions by exposing tools for schema description, SQL checking, and safe query execution.

A sample MCP server implementation for Next.js projects that uses the Vercel MCP Adapter to handle protocol requests across different transport methods.

A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.

Provides a secure workspace for AI-driven file management and Python script execution designed to run on Vercel. It enables tools for full file operations and code execution within a sandboxed environment.

Integrates ElevenLabs Text-to-Speech capabilities with Cursor through the Model Context Protocol, allowing users to convert text to speech with selectable voices within the Cursor editor.

Lets AI assistants use MetaModel's formula engine for certified computation, turning published calculators, pricing tools, and engineering models into AI-callable tools with no hallucinated math.

Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.

Enables local agents to connect to and interact with Google Colab sessions running in the browser.

Bridges a local AI agent to a Colab session in the browser, enabling code execution and file operations through the Model Context Protocol.

Enables agents to perform recorded, snapshot-evidenced computer-use and browser-use in a fresh, disposable VM, with interruptive actions judged by the agent.

A demonstration server that reveals security risks by accessing sensitive environment variables, illustrating how MCP tools can potentially leak user data without explicit consent.

Gives AI agents a browser that bypasses bot detection, a MITM proxy for traffic interception, and a Python sandbox to autonomously write and execute security exploits.

An MCP server for bridging your local agent to a Colab session in the browser.

A fully featured coding agent that uses symbolic operations (enabled by language servers) and works well even in large code bases. Essentially a free to use alternative to Cursor and Windsurf Agents, Cline, Roo Code and others.

Enables AI assistants to read, build, and edit 247afk scripts in real-time through a local WebSocket bridge. It allows for live manipulation of block editor content directly within the browser.

Enables agents to open or connect to a Colab browser tab and use notebook tools, resources, prompts, and progress through a local stdio session.

Provides a headless session runtime for reactive compute graphs, enabling MCP-driven cell operations without a DOM or browser.

An MCP server implementing AI-user confirmation protocols, providing tools for LLMs to seek user confirmation when uncertain through yes/no questions, action confirmations, intent clarification, understanding verification, and satisfaction ratings.

Build agent skills where you work — write a script, add a SKILL.md, and use it in Claude Code/codex/Cursor immediately. The same fixed entry point that runs locally deploys to production without a rewrite.

MCP Server for the Peacock extension for VS Code (https://peacockcode.dev), coloring your world, one Code editor at a time. The main goal of the project is to show how an MCP server can be used to interact with APIs.

Bridges a local agent to a Colab session in the browser, enabling seamless interaction with Colab from local clients.

Enables AI agents to observe and control a browser-based 2D robot simulator, including driving, configuring sensors and modules, running programs, and generating wiring, firmware, and parts lists for ESP32, Arduino Uno, or Raspberry Pi.