"Understanding VS Code Agents or Extensions" matching MCP servers:

A bridge that enables AI assistants to connect to VS Code's debugger, allowing them to interact with and control debugging sessions through websocket connections.

MCP server that integrates with VS Code to enable file operations, git diffs, and line highlighting via MCP clients like Claude.

Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.

Enables Claude Code to delegate tasks to OpenAI's Codex CLI (GPT-5.4) with structured execution traces, parallel execution, session persistence, and adversarial code review.

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

Exposes PICO XR building blocks as MCP tools, enabling AI agents to programmatically configure XR scenes for PICO devices through idempotent, non-destructive operations.

Enables local video inspection and offline transcription with timestamped JSON and Markdown output, enforced filesystem boundaries, and reproducible content-addressed caching.

Token-safe code search for AI agents: queries the language-server index (clangd / Roslyn / tsserver / pyright) instead of grep and returns a token-capped file:line list — ~20x fewer tokens. Symbol-level editing + a grep→index rewrite hook. Local-only, no IDE.

Controls Visual Studio 2022 through MCP using COM/DTE automation, enabling file management, building, debugging, and breakpoint operations directly from Claude Code.

MCP server providing governed access to board meeting data, with tools to query meetings, motions, and documents, automatically applying anonymity policies before returning answers.

Enables an orchestrator like Claude Code to hand coding work off to Cursor SDK agents, run as detached background jobs that survive the session and can be listed, inspected, steered, resumed, or stopped. Agents are asynchronous and reusable across follow-up turns, letting expensive frontier models delegate cheaply without blocking or paying to read the results.

Ultra-fast local markdown documentation RAG for AI coding agents, enabling instant BM25 search over official framework docs and live AI model registries via MCP.

Enables an AI agent to launch, monitor, and steer multiple coding agents running in tmux panes, including sending keystrokes, waiting for idle or output patterns, and managing sessions.

Enables AI agents to manage KVM/libvirt virtual machines and Borg/Timeshift backups on Fedora, with sudo and destructive operations flagged for confirmation.

Enables local deterministic discovery, validation, and selection of validated skills through MCP tools, producing consistent plans without executing any skill.

Provides AI assistants with VS Code integration for file operations, command execution, project analysis, and development workflow automation.

Enables orchestrating multiple specialist Claude Code agents as a team, with live visualization and agent-to-agent messaging.

A local markdown memory and cross-agent context engine for AI coding assistants. It provides an MCP server with tools to search, add, retrieve, and distill persistent memory across tools like Claude Code, Cursor, and Zed.

Enables external agents to run, edit, create, and manage the Jupyter notebook the user is actively editing in VS Code, headlessly and without approval dialogs. Works with any MCP client and is Jupyter-optional for document operations.

A unified MCP-compatible system for controlling fleets of remote machines through AI agents.