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

Enables a browser-based AI assistant to read code, edit files, run tests, inspect failures, and keep task checkpoints on a local project.

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

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.

A server that enables browser-based local LLM inference using Playwright to automate interactions with @mlc-ai/web-llm, supporting text generation, chat sessions, model switching, and status monitoring.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

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.

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.

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.

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.

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

An advanced Playwright MCP server that enables efficient browser automation through compressed accessibility snapshots, sandboxed code execution, and visual element labeling. It features 90% DOM compression and integrated DevTools for deep web inspection and interaction.

Lets a frontier coding agent delegate research, cataloguing, and long-running computation to a local LLM with guarded filesystem, web, and Python execution tools, preserving the agent's context and tokens.

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

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

MCP server that wraps Codex CLI as a subprocess, exposing code execution, web search, and structured output as Model Context Protocol tools.

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

Lightweight MCP server for After Effects that enables Cursor Agent to execute ExtendScript code inside AE via a single tool, similar to Blender MCP.

Remote-control Unity Editor from any AI IDE via file-based IPC — 62 tools, zero dependencies

Provides direct, unsandboxed local machine access via filesystem, Python, Node.js, and shell commands for MCP agents.

Provides structured spec-driven development workflow tools for AI-assisted software development with sequential spec creation (Requirements → Design → Tasks). Features a real-time web dashboard for monitoring project progress and managing development workflows.