The task manager for Continue
Give Continue (continue.dev) a real task queue. TaskPrio is MCP-native — add one mcpServers entry to your config.yaml and Continue's agent pulls the highest-priority task with get_next_task, works it, reports a result, and grabs the next one. You set the order; it runs the list on autopilot — and you watch it work in a live cockpit.
Connect in three steps
1. Open the board, then the sidebar foot, and Copy token. 2. Download the bundled server. 3. Add it to Continue's config.yaml:
# download the MCP server
curl -fsSL https://taskprio.com/mcp-server.js -o ~/.taskprio-mcp.js
Then add this to your Continue config.yaml (or a .continue/mcpServers/taskprio.yaml file):
mcpServers:
- name: TaskPrio
type: stdio
command: node
args:
- ~/.taskprio-mcp.js
env:
PROMPTPRIO_API_TOKEN: pp_your_token
PROMPTPRIO_API_URL: https://taskprio.com
Reload Continue and the tools are live. (Full details in the docs.)
The autopilot loop
Once connected, point Continue's agent at your queue and it runs top to bottom — auto-scoping to the project your workspace is in (it reads the working directory, no manual setup):
1. get_next_task → top unblocked task + merged project context
2. (Continue does the work in your repo)
3. complete_task → short result, logged as an audit trail
4. repeat → until the queue returns no task
Hit a blocker? Continue calls flag_needs_human and moves on, so one stuck task never stalls the whole run.
Why a queue beats a prompt dump
- One priority order — Continue always knows the single next thing, even across 1,000+ tasks and many projects.
- Context comes with the task — each task carries its project's merged instructions, so you stop re-pasting setup into the agent.
- Parallelise across sessions (Pro) — run up to 5 Continue sessions on the same project and the queue divides itself: each session leases the next unclaimed task, so five work the top five in parallel — no partitioning, no two agents on one task.
- You stay in control — capture tasks in the Inbox, rank what matters, and Continue only works what you've ranked.
Frequently asked questions
Does Continue support TaskPrio's MCP server?
Yes. Continue supports MCP servers in its config.yaml under mcpServers. Add TaskPrio as a stdio entry (command: node, args: ~/.taskprio-mcp.js) and Continue's agent gains TaskPrio's tools.
How do I give Continue a task queue?
Download the MCP server, add it to config.yaml as an mcpServers stdio entry with the env var PROMPTPRIO_API_TOKEN, and Continue's agent can call get_next_task, complete_task and friends to pull from and complete tasks in your TaskPrio queue.
Can Continue work tasks on autopilot?
Yes — it loops get_next_task → work → complete_task until the queue is empty, a task is blocked, or you stop it.
Is it free?
Yes. Free includes 1 MCP session and 50 completions/day; Pro ($10/mo) gives 5 sessions and unlimited completions.
Start free — no card → Using Claude Code? →
Run it on autopilot. Paste our maintained autopilot prompt into Continue — it adds hard safety gates (money / credentials / publishing stay manual), an empty-queue stop, and auto-scopes to your project.
view ↗Done for now? Paste the stop prompt to end the session cleanly — it lands the current task (done-with-proof or a resume note), syncs the queue true, banks one learning, and leaves you a short report.
view ↗