ZERNO Lite

Connect AI agents to your ZERNO product backlog over a secure remote MCP endpoint.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Zerno Get Project Brief: Short project brief: name, slug, stage, one-liner, current focus, next best action, up to 5 do-not-do items, and compiled memory index. Call once at session start when you nee
  • Zerno Get Agent Context: Fetch compiled project memory for an agent run: memory index, recent articles, recent session events, and a markdown context block. Pass related_task_id for task-specific memo
  • Zerno List Tasks: List backlog tasks for this project. Filter by status[] (e.g. ['backlog','ready','in_progress','at_agent']), priority, theme, score presence, staleness. Returns full task objects (ca

What data it sees

Do you need an account

No: the server works without sign-in

Connect AI agents to your ZERNO product backlog over a secure remote MCP endpoint. Read project briefs, list and open tasks, retrieve compiled project memory, patch task status, submit triage proposals, and file agent-intake tasks. OAuth 2.1 (PKCE), per-project authorization. 8 tools, no resources or prompts.

How to connect

How to connect ZERNO Lite to Claude

The server address to paste into Claude settings:

https://one--zerno.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect ZERNO Lite to ChatGPT

The server address to paste into ChatGPT settings:

https://one--zerno.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect ZERNO Lite to Cursor

The server address to paste into Cursor settings:

https://one--zerno.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (8)

Raw names from tools/list. Only developers need these.

zerno_get_project_briefShort project brief: name, slug, stage, one-liner, current focus, next best action, up to 5 do-not-do items, and compiled memory index. Call once at session start when you need orientation; do NOT call before every task — list_tasks/get_task carry their own context.
zerno_get_agent_contextFetch compiled project memory for an agent run: memory index, recent articles, recent session events, and a markdown context block. Pass related_task_id for task-specific memory.
zerno_list_tasksList backlog tasks for this project. Filter by status[] (e.g. ['backlog','ready','in_progress','at_agent']), priority, theme, score presence, staleness. Returns full task objects (capped by `limit`, default 50). Prefer narrow filters and a small `limit` to keep responses compact; get_task is only needed to fetch a task by its UUID.
zerno_get_taskFull detail for one task: title, status, acceptance criteria, file paths, attachments, plan/report if any.
zerno_update_taskWrites: mutates the task in place (status transitions are validated; ICE is recomputed when any score changes) and records an audit event. Patch task fields: title, status, priority, importance_score, impact_score, effort_score (each 0-10), product_moving (★ flag), theme tag, agent_notes. The executor is controlled by the task assignee, not scoring. Use this for workflow status changes and human-confirmed edits; agent-proposed classifications should go through submit_task_triage.
zerno_submit_task_triageSubmit AI triage proposals for one or more backlog tasks. Each item is stored as a `pending` suggestion (size/readiness/risk/type/next_action/reason); the underlying task is NOT mutated. A human accepts or rejects from the web UI. Use after analyzing the inbox to write back classifications in one call.
zerno_create_agent_intake_taskWrites: creates a NEW task in `review` status. File a review task from an ad-hoc implementation report — used when the agent performed work outside an existing task and wants to register it in the backlog for human review. Not for normal backlog decomposition.
zerno_capture_session_eventWrites: appends a new event into compiled project memory. Adds a concise session summary/event. Useful from agent hooks or at the end of a coding session when no run_id lifecycle is active.