"How to fetch or scrape data from a website for use in training an LLM" matching MCP servers:

Enables clients to interact with a bundled documentation corpus through MCP tools and resources over HTTP or stdio, and provides a trajectory evaluation harness for grading agent performance.

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 see, locate UI elements, and operate any Windows desktop app through natural language, using accessibility-tree matching with optional vision-model fallback, plus an autonomous visual loop with introspection and meta-learning.

An MCP server for Microsoft's Cognitive Services Custom Vision Training API that enables AI agents to create, train, and manage custom image classification and object detection models through natural language interactions.

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 MCP server that lets Claude Code consult stronger AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner) when you need deeper analysis on complex problems.

Blind multi-model councils with anonymous LLM seats and direct 1:1 chat as a local MCP server. Enables asking one question to get independent answers from multiple model CLIs, then blind scoring and reveal.

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

Centralized encrypted gateway that routes requests to 11+ LLM providers (API keys and CLI subscriptions) through a single OpenAI-compatible endpoint, with MCP tools for vault operations, code search, and shared state.

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

MCP server that provides a live coordination layer for AI agents, including attributable handoffs, a shared event ledger, atomic work-claiming, and advisory file leases to prevent collisions.

An MCP server that provides LLMs access to other LLMs

Enables AI agents to debug and repair historical Solaris/SPARC systems by providing an out-of-band control plane with guest DTrace, QEMU monitor access, SPARC-aware GDB, host eBPF/perf tracing, and an immutable evidence ledger for cross-layer hypothesis testing.

Enables Claude Code as a team leader to delegate tasks to GPT and Gemini experts, supporting multi-LLM collaboration with tools for consultation, code review, design, and background execution.

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 browser automation through MCP clients like Claude or Cursor, using the client's existing LLM without requiring an additional API key.

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

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

A lightweight, local MCP server for Mac that replicates a 3-stage LLM council workflow using OpenRouter, enabling multi-model deliberation and synthesis directly from AI coding tools.

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.