Things AI: AI-first Things 3 CLI and MCP server for macOS

Things Cloud CLI and MCP server for Linux and macOS, with task sync and plugins for Codex, Claude Code, and Cursor.

A rich MCP server for Things

MCP server for Things 3 task management via URL Scheme

Model Context Protocol server for Things 3 task management integration

Let your AI assistant run Things 3 on your Mac: no duplicate to-dos, no stolen focus, 5 ms reads.

Awesome swiss knife for Things3 – MCP server for AI, CLI, HTTP API, JS/TS API and Web

Artifacts for any coding agent. Publish what Claude Code, Codex, Cursor or Gemini CLI builds to a durable link, with versions and comments on the page.

Artifacts for any coding agent. Publish what Claude Code, Codex, Cursor or Gemini CLI builds to a durable link, with versions and comments on the page.

MCP server for Things 3 with read/write support for tasks, projects, areas and tags.

MCP server for Draw Things - local AI image generation on Mac

MCP server for Draw Things - local AI image generation on Mac

MCP server for Things 3 with read/write support for tasks, projects, areas and tags.

Search local events in plain words: JS and Python clients, MCP setup and examples for the Things To Do API

GTD Brain for Gemini CLI — your Getting Things Done board as a Gemini CLI extension: hosted MCP server (OAuth email-code sign-in), GEMINI.md context file, /gtd:* commands

An MCP server to control all things Mac

Minimalist AI agent that fixes itself when things break.

A small mcp service to record things in sqlite. A simple GPT memory layer. ;)

Where your AI assistant helps you think things through.

Things related to artificial intelligence built on top of Nasdanika capabilities

Agent commerce protocol — how AI agents buy things

An MCP server for Dataverse people who know where this thing is coming from.

An MCP-native workflow engine that teaches your agent how you like to get things done.

Find interesting things to explore in a place with the help of AI. Built with Gemini, Nextjs, Zod.

MCP server with 21 tools for things AI is bad at — math, hashing, encoding, date arithmetic, and more.

Db oriented agent story game thing, lol. Made with ef core for LM Studio characters.

Public MCP server for Paris: events, places, free things and booking links. Read-only, no key.

BG, gone. FOSS background removal on open models. Free previews, pay by the image in USDC, or self-host the whole thing.

Read-only Gmail for Claude, provably. It can read your inbox and cannot send, delete, or modify a thing.

🪶 A polite, suspicious web scraper for AI agents. Collects the shiny things, leaves the junk, trusts nothing. CLI + library + MCP server.

Find the next thing to build on GitHub - before everyone else does. An MCP server that surfaces underserved problem spaces.

A retrieval system that lets you just ask questions about IIT Kanpur's academic policy manual instead of reading the whole thing. Built as a RAG pipeline with an MCP server.

aion.ly: where people and their agents discover and discuss all things AI, together. Open source, no ads, no hidden algorithms. A Chatcode Lab project.

A simple MCP (Model Context Protocol) server that makes LLMs ready for new things by exposing tools to convert websites and documents into LLM-ready Markdown.

Real-time music visualiser + MCP server. Listens to MIDI or audio, draws it in a Western-music-theory visual language, and exposes the whole thing to Claude Desktop for natural-language control.

MCP server that detects cross-signal correlations in project health — the thing no individual check can tell you.

Point-and-talk feedback capture for AI analysis. Share your screen, click on things, say what you think.

Agent MCP Router MCP — one router for the whole MEOK fleet. Holds 62 MEOK MCPs behind one namespaced endpoint. Install ONE thing, get all of them. By MEOK AI Labs.

A token-lean MCP memory server: a knowledge graph your AI agent can search without reading the whole thing. Drop-in replacement for @modelcontextprotocol/server-memory.

A token-lean MCP memory server for AI coding agents: a knowledge graph your agent can search without reading the whole thing. Drop-in replacement for the reference memory server.

🔻 The agent's data reader: any JSON/JSONL/CSV/TSV blob becomes its shape and the slice you asked for, not the whole thing. Zero-dep, CLI + web + MCP.

Point at things in your running app, say what's wrong, and hand your coding agent a brief it can act on. Zero-dep web component, Angular adapter, MCP server.

Policy / contract layer for AI development. MCP gives AI hands, Skills gives AI experience, Guard makes sure AI does not do the wrong thing. Rust + MCP server. One-line install into Cursor / Claude Code.

Give your AI your whole life. Keep your private things private. Olympus runs on your Mac, Omarchy or Ubuntu 24.04 LTS computer and works with ChatGPT, Claude, Grok, Codex, Claude Code and any app that speaks MCP.

The Loss-Prevention Friction Engine for Founders. An AI-powered MCP server that stops you from building things nobody wants using clinical analytics, behavioral pattern scanning, and real-time market intelligence.

Stop repeating how you want things done. Varyz learns how you work from your past AI chats and briefs Claude Code, Codex and Cursor before every task. Local-first and open source.

Don't build it alone. Before the agent writes a line: what exists, who won, what nobody has, a merge plan for the duplicates, and the person working on the same thing. MCP server.

A real interactive terminal for AI agents (MCP). Run and test vim, htop, gdb, REPLs, and any TUI — things the built-in fire-and-forget terminal can't touch.

MCP server that carries what one session learned into the next. A per-project ledger written as things happen, scored per task by TypeSafe's Jev evaluation model via the Vercel AI Gateway.

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.

EDK-1, a foundation model of the physical world trained on 30 billion images. Your agent can find any object, condition, event or living thing on Earth, read what's true there, route around it, and get alerted when it changes.

Your design system says one thing, your product ships another. Compare tokens from any design tool (Figma, Sketch, Penpot), live sites & apps, or codebases — get conflicts, confidence scores, and WCAG drift checks. CLI + library + MCP server.

MCP server for where things were, then: which US county held a place on a date (Newberry county-boundary atlas via OpenHistoricalMap), federal land descriptions and PLSS locations, and the route from a land patent to its case file.

A spending guard for AI agents that pay for things: budgets, payee allowlists, price-spike checks and human approval before any payment leaves the wallet. Pays HTTP 402 (x402) paywalls in USDC on Circle's Arc and in NEAR.

Self-hosted wellness OS. A coaching team reads your labs, lifting, running, food and sleep as one picture, suggests the one thing worth doing today, and makes the small calls with a one-tap Undo. PWA + REST + MCP. No scores, no nudges.

Gives your AI assistant your career history: it saves and scores job postings, tailors a resume to each one from things you actually did, renders the PDF, and tracks your applications. Needs Maestro Career Studio running on your computer: uv tool install --python 3.12 maestro-career-studio, then maestro start. 88 tools; your data stays on your machine.

A file organization tool that auto generates simple descriptions for every file and folder, updating them in real time as things change. Supports all file types, manual edits, and now exposes descriptions to AI assistants via an MCP server, so you and your AI tools can navigate messy directories without opening everything.

Security suite for AI agents — catch the dangerous thing before it's signed. Preflight an unsigned EVM transaction for drains, inspect EIP-712 signatures for permit-phishing, and gate agent actions by policy. Pairs with any wallet or MCP stack; ships a non-custodial wallet too.

For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in before it writes, and the result is verified against your spec after, so those three are earned, not assumed. First L4 implementation of the Ironclad standard.