"How to access a web browser" matching MCP servers:

Enables coding agents to query the dependency graph of a GitHub backlog, retrieve ordered ready work and prerequisite chains, atomically claim issues, and report blockers—so agents work in the correct order and safely in parallel.

A production-ready Model Context Protocol server implementation that connects AI assistants to the TON blockchain, allowing them to query wallet balances, transaction details, smart contracts, and other blockchain data.

Enables MCP clients to run complete browser workflows through a single run_workflow tool, with anti-detection backends, intelligent element location, automatic retries, and session persistence.

Enables AI agents and MCP clients to translate high-level web automation goals into deterministic, resilient browser selector action sequences. It runs as a zero-dependency Python MCP server that returns structured execution plans and telemetry for agentic workflows.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

Enables real-time user intervention for MCP agents through a web UI, allowing users to review context and provide feedback when AI agents drift from intent, keeping them on track.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Discover and connect your agents with other agents via A2A protocol. Share resources for free or fee.

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.

A sandboxed computer-use MCP server that lets an AI agent drive a real browser and desktop apps, confined to a nested X11 window so it cannot touch your real screen or files.

A Python code execution sandbox based on IPython and Docker. Stateful code execution, file transfer between host and container, configurable network access.

A deterministic Mastermind-style cipher lock exposed as MCP tools for benchmarking LLM reasoning and tool-use through a legible duel.

A local stdio MCP server that exposes compact semantic observations from UI elements annotated with data-agent-* hints, designed to work alongside the official Playwright MCP for browser automation.

Enables AI agents to participate in meetings by pulling pending requests, reading context, and submitting answers through a Supabase-based MCP server.

An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.

Enables external agents to deliver queue, steer, and task messages to a running dsh web instance and query session status, with configurable trust and dangerous-command filtering.

Mandatory human approval gate for autonomous AI agents. Before any critical, irreversible, or financially significant action executes — file deletion, production deployment, financial transaction — the agent calls oracle_validate. A human receives a real-time Telegram notification with full context and taps Approve or Reject. The agent waits for the decision before proceeding.

A lightweight, stealthy headless browser for AI agents, providing MCP tools for web extraction, interaction, and snapshotting.

An MCP server that enables local AI models to receive guidance from remote 'senior' AI providers like OpenAI, Anthropic, and Gemini to solve programming problems. It features intelligent multi-turn dialogue management, context synchronization, and automated session history tracking.

Enables a host AI agent to trigger a multi-agent debate, running N-rounds where agents critique each other's answers, then synthesizes a consensus recommendation with ranked options.