"Controlling a Windows host" matching MCP servers:

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 Desktop to control mouse, keyboard, and clipboard on Windows, allowing AI-driven computer interaction tasks like clicking, typing, scrolling, and screenshotting.

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.

Enables AI models to control a local Windows desktop by moving the cursor, clicking, scrolling, typing Unicode text, sending key chords, and capturing screenshots. Runs natively on Windows with minimal latency and no heavy dependencies such as Python, PyAutoGUI, or Docker.

A Windows-only MCP server that gives AI models eyes and hands on a Windows machine, enabling file reading, screenshots, mouse/keyboard injection, and an auto-debug loop with a safety-focused watchdog for protected abort regions.

Self-host a realtime voice-call companion for coding agents. Exposes an MCP endpoint that agents can poll as an alternate input stream.

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.

Connects any MCP host to the Haven Agent Gateway, enabling session creation, agent discovery, collaboration, handoff, and work operations through MCP tools over stdio or Streamable HTTP.

An MCP server that lets LLM agents autonomously play retro games by driving a real OpalEmu emulator in a Playwright-controlled browser, exposing tools for loading ROMs, controlling buttons, and capturing screenshots.

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

Coherence guard for shared files: when two agents write the same file, the stale writer is denied instead of silently overwriting, then reacquires and retries. Single-host, TLA+-verified.

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.

A secure, containerized workspace for LLMs to autonomously code, test, and debug projects without risking the host machine.

Enables a structured multi-perspective deliberation workflow where three independent advisors propose strategies, cross-examine one another, and a final arbiter converges on a verdict, with all generation performed by the host agent.

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.

OS keychain secrets for AI coding agents, over MCP. Anchors credentials to the native vault (macOS Keychain, Linux Secret Service, Windows Credential Vault) and exposes them through 44 policy-governed tools: per-environment values, TTL, linked rotation, encrypted transfer bundles, redacted exec, and a tamper-evident audit log. Local-first, no cloud account.

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 any MCP host to drive durable, always-on agents that run server-side on the Highway Workflow Engine via three tools: run_goal, get_status, and approve.