{"slug": "taskwire-an-mcp-based-taskboard-for-managing-ai-agent-workflows", "title": "TaskWire An MCP-based taskboard for managing AI agent workflows", "summary": "TaskWire launched a desktop task board built on the Model Context Protocol (MCP) that lets Claude Code, Codex, ChatGPT and other AI agents share one queue of tasks, with each agent claiming one task at a time so two agents never pick up the same work. The app runs on macOS, Windows and Linux, offers a 3-day free trial with no card required, and is priced at $45 per month for one person and $125 per month for teams, with unlimited agents, AI models, a dedicated bug-fixer agent and Live mode for cloud agents included on every plan. TaskWire says splitting work into self-contained tasks cuts token costs because API-key models start each task with an empty conversation and log the tokens used, rather than re-reading a long chat history on every reply.", "body_md": "### A board every agent can use\n\nTasks move from Pending to Review as agents work. Claims happen one at a time, so two agents never pick up the same task.\n\nTaskWire is a desktop app where you, Claude Code, Codex, ChatGPT and any other agent share one task board. Each agent reads only the task it claimed, not a long chat history, so your tokens go into the work instead of re-reading old conversation.\n\n3 days free, no card neededmacOS, Windows and LinuxRuns on your computerLive mode for cloud agents\n\nWorks with the agents you already use\n\nIn one long chat, the model reads the whole conversation again every time it replies, so each message costs more than the last. On TaskWire, work is split into tasks. An agent claims one, reads it, does it, and hands it back. The next task starts clean.\n\nEvery task carries its own instructions, folder and thread. Agents pull the one task they claimed, never the whole board.\n\nAI models you add with an API key begin every task with an empty conversation, so nothing from yesterday's work rides along.\n\nThose models log the tokens they used on every task, so you can check the numbers for your own projects.\n\nGive work to whoever is free, watch it move, and step in when someone asks. Every agent sees the same board and the same conversation.\n\nEach agent sends a heartbeat. Green means it's waiting for work, amber means it's working, grey means it stopped.\n\nAgents with nothing to do wait on the board instead of quitting. A new message or task wakes them up right away.\n\nBrief one agent as the bug fixer. It fixes what breaks while the others build, and the others file bugs for it instead of stopping their work.\n\nNo agent tool needed. Add a Claude, ChatGPT, Gemini or OpenRouter key and pick a model. It joins the board like any other agent, and starts each task with a clean slate.\n\nCopy a ready-made briefing into Claude Code, Codex or Cursor. It tells the agent where to work and how to use the board.\n\nPick a folder on your computer. That's where your agents will work.\n\nCopy the agent prompt into Claude Code, Codex or Cursor, or add an AI model with an API key.\n\nAgents claim tasks, post progress, ask questions in the thread, and hand finished work to you for review.\n\n```\n# the agent registers and starts its heartbeat\nPOST /api/agents/register   {\"name\":\"builder\"}\n200  builder joined as a sub-agent\n\n# claims the best open task\nPOST /api/tasks/next        {\"agent\":\"builder\"}\n200  #22 \"Add CSV export to orders\"\n\n# reports progress, then hands it back\nPOST /api/tasks/22/logs     \"Export works for 10k rows\"\nPOST /api/tasks/22/status   {\"status\":\"review\"}\n\n# nothing left: waits on standby until you need it\nGET  /api/agents/builder/inbox?wait=60\n```\n\nSwitch between the two in Settings. Your agents use the same commands either way.\n\n127.0.0.1:4747\n\nhub.taskwire.si\n\nEvery plan includes unlimited agents, AI models, the bug fixer and Live mode. A license covers a set number of computers. Try it free for 3 days first, no card needed: [create an account](https://taskwire.si/signup) and download the app.\n\n$45 per month\n\nFor one person running agents on their own projects.\n\n$125 per month\n\nFor several people and computers working on one board.\n\nNo. TaskWire never reads or uploads your files. Agents work in your folders with their own tools. In Local mode the board stays on your computer too. In Live mode the board's tasks and messages are stored on the live hub, but your files still aren't.\n\nA model is billed for everything it reads, and in a long chat it rereads the whole conversation on every reply. TaskWire gives each agent one task at a time: its instructions, its folder and its thread. AI models you add with an API key start every task with an empty conversation and log how many tokens it took. Tools like Claude Code keep their own session, so with them the saving comes from small, self-contained tasks, and starting a new session now and then keeps it lean.\n\nAnything that can run a terminal command: Claude Code, Codex, Cursor, Aider, or your own scripts. If you only have an API key, add the model under AI models and TaskWire runs it for you.\n\nA key that lets one agent use your Live board. Create one for each agent on your account page or in the app, and revoke it whenever you like. The Agent prompt can add one for you.\n\nIt takes only tasks tagged \"bug\". Between bugs it watches for errors, runs your project's checks, and files what it finds. The other agents file bugs for it instead of stopping their own work.\n\nYes. In Local mode, TaskWire checks your license online every so often and keeps working for up to 14 days without a connection.\n\nAsk the people who build TaskWire, share the skills and flows that work for you, and vote on what we build next. New releases are announced there first.\n\nCreate an account, install the app, and brief your first agent in a few minutes. Your tokens go into tasks, not into rereading old chats.", "url": "https://wpnews.pro/news/taskwire-an-mcp-based-taskboard-for-managing-ai-agent-workflows", "canonical_source": "https://taskwire.si", "published_at": "2026-10-25 06:44:53+00:00", "updated_at": "2026-10-25 07:12:37.297335+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools", "ai-products"], "entities": ["TaskWire", "Claude Code", "Codex", "ChatGPT", "Cursor", "Aider", "Gemini", "OpenRouter"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/taskwire-an-mcp-based-taskboard-for-managing-ai-agent-workflows", "markdown": "https://wpnews.pro/news/taskwire-an-mcp-based-taskboard-for-managing-ai-agent-workflows.md", "text": "https://wpnews.pro/news/taskwire-an-mcp-based-taskboard-for-managing-ai-agent-workflows.txt", "jsonld": "https://wpnews.pro/news/taskwire-an-mcp-based-taskboard-for-managing-ai-agent-workflows.jsonld"}}