Verify that browser profiles are actually isolated from one another instead of assuming it - confirm each profile's timezone agrees with its own exit IP, that WebRTC exposes only the proxy, that canvas and WebGL hashes stay identical across relaunches of one profile, and that no two profiles share a

DeepSeek Harness bridge plugin: exposes the newest Zhipu/Z.AI coding-plan models (e.g. glm-5.3) on the zai-coding-cn route before the bundled pi-ai catalog catches up.

Claude Code plugin that exposes Codex CLI's built-in imagegen skill as /codex-image:* user-invoked slash commands.

High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Shared server-side core for MulmoClaude and MulmoTerminal — the always-shipped-together subsystems consolidated behind subpath exports so the two hosts can't drift. Server-only except the browser-safe ./artifacts, ./whisper/client, ./workspace-setup/slug,

Headless Angular components from the 4SH Design System: signals + Angular CDK, styled exclusively through design tokens. Ships a companion MCP server exposing the kit catalog and doc to AI coding agents.

Model Context Protocol server transport: serve typed procedures as MCP tools to Claude and other MCP clients, with streaming progress, list_changed and an expose policy.

Agent skill for repository-aware social preview images, visual directions, and GitHub-ready exports.

Exposes 20 tools over stdio that let coding agents treat any SSH-reachable machine as a local workspace: reading, writing, editing, searching and listing files, running commands and background jobs, driving persistent terminals, and forwarding ports over one pooled connection, with nothing installed on the remote host.

Enables MCP-capable coding agents to act as a deterministic technical art director and multi-engine pipeline builder, locking AI-generated 2D/2.5D game assets to consistent camera angles, palettes, rigs, atlases, and exports across Blender, ComfyUI, UniRig, LibreSprite, Godot 4, Unity, and Unreal Engine 5.

Exposes the battle.training agent tank arena API as MCP tools, letting clients read ladder standings, bot ratings, recent matches and replay URLs, and inspect cup info. With an API key it also enables registering bots, uploading smoke-tested controller versions, and enrolling in sponsored cups.

Exposes local recommendation tools over MCP so clients can rank groceries with explainable scoring across nutrition, price, promotions and close-to-expiry offers. Also supports configurable offer monitoring, weekly plan digests and deduplicated notifications backed by SQLite state.

A stdio MCP server that lets AI coding tools on a Mac speak text aloud through the local Speaklna text-to-speech app. It exposes four tools (speak, stop, status, voices) so agents can voice replies, halt playback, check state, and list available voices, but cannot import voices or change settings.

A local, stdio-based MCP server that lets AI agents create and maintain a brand project through typed tools covering identity, palette, typography, voice, assets and guide chapters, then validate it and export a self-contained, client-facing static guidelines site that can be hosted anywhere.

Enables an AI assistant to read a project's git diff and generate Angular-style, company-standard commit messages, then stage and commit the changes on the user's behalf. It runs on the host's built-in AI capabilities with no API key or cost, exposing tools for fetching changes, staging all files, and committing.

Exposes 16 local stdio MCP tools that give Codex-style clients project-isolated persistent memory, local ONNX-based semantic search, and durable task tracking that survives across sessions and concurrent clients, without executing agents, hosting a model, or contacting model providers.

It exposes a single slugify tool over remote MCP Streamable HTTP and a matching OpenAPI 3.1 endpoint, enabling clients to generate URL-friendly slugs through a stateless Cloudflare Worker.

Enables local access to personal banking data such as accounts, balances, transactions, and CSV exports, with optional preview and confirmation of transfers between the user's own accounts, including credit cards and pensions. Requires Node.js 22+, a customer account, and a personal API client with BankID login.

Enables MCP clients to drive a local Windows avatar interface, switching between an energy core and holographic face, triggering expressions, and reacting to microphone volume through seven exposed tools. It serves an animated visual panel over localhost with SSE updates while conversation stays in ChatGPT.

Enables CLI agents to fold source documents into a cited Markdown knowledge base using an ontology, exposing tools to list, read, search, lint, and write pages only after user approval.

Exposes the Jupyter notebooks open in VS Code to MCP-compatible AI agents, letting them edit cells in the open editor and execute them in the live kernel without file conflicts. Agents can make partial edits, track stale cells, inspect variables, and manage kernels while preserving the user's interpreter choices and unsaved work.

Enables AI clients to drive local video editing projects through a CEP bridge, covering media ingest, sequence and timeline editing, effects, keyframes, captions, markers, audio, color, and exports across hundreds of discoverable tools. Ships context resources, guided prompts, and higher-level assembly workflows for agent-driven editing.

Enables coding agents on different machines to exchange end-to-end encrypted messages through a shared, self-hosted relay, exposing inboxes, room history, and notifications to Claude Code, Codex, or any MCP client. Peers' messages arrive automatically as clearly framed untrusted data, so collaborators can coordinate without granting tool, file, or command access.