zerno_get_project_briefLABSCO SUMMARY
The orientation an agent is missing: what the project is for, and what not to touch.
The brief arrives with a next action and a do-not-do list, and everything the agent proposes lands as a proposal a human approves rather than a change already made. Authorization is per project, and a read-only token cannot even see the writing tools.
What it is
A remote server for ZERNO project context: the project brief, compiled agent memory, the task backlog, and structured ways to write back — task updates, triage proposals, intake tasks and session events.
What you get
- A project brief: current focus, next action, do-not-do list, memory index
- Compiled project memory plus recent events, assembled for one agent run
- Backlog listing with filters, and full detail on a single task
- Task fields and status patched, with the ICE score recomputed
- Triage proposals submitted and held for human approval rather than applied
- A review task filed from an agent's report
- Session summaries appended to project memory
- Tools/list filtered by scope — a read-only token sees only the four read tools
Requirements
A ZERNO project and OAuth with PKCE; the client registers itself dynamically, so there is no static API key to paste. The endpoint is https://zerno.one/mcp over streamable HTTP, and user-scoped tokens need a project_slug such as zerno-one.
Setup effort
One command, then sign in — codex mcp add zerno --url https://zerno.one/mcp, then approve the OAuth sign-in
USE CASES
01
Getting an agent oriented before it writes code
The brief gives focus, next action and the do-not-do list; the agent context adds compiled memory and recent events.
02
Picking the next thing to work on
Filter the backlog, then read the one task in full rather than guessing from its title.
03
Recording progress on a task
Patch the fields and status; the ICE score is recalculated rather than left stale.
04
Proposing a backlog change without applying it
Triage proposals sit pending human approval, so an agent can suggest reprioritisation safely.
05
Filing what an agent found for someone to review
An agent report becomes a review task in the backlog instead of a message that gets lost.
06
Carrying what happened into the next session
Append a session summary to project memory so the next run starts from it.
8 tools
Listed in project docs. Your client may show a different list.
zerno_get_agent_contextzerno_list_taskszerno_get_taskzerno_update_taskzerno_submit_task_triagezerno_create_agent_intake_taskzerno_capture_session_eventBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
A ZERNO account and an authorized project
INSTALLATION
Connect your client
Server setup
Setup
Add a remote connector named zerno with URL https://zerno.one/mcp
Complete the OAuth consent in the browser
Tell the agent which project with a project_slug (e.g. zerno-one) for user-scoped tokens
Or add the hosted endpoint with one command
Codex
TERMINAL
codex mcp add zerno --url https://zerno.one/mcpHosted endpoint
ENDPOINT URL
https://zerno.one/mcpAdd this hosted endpoint to your MCP client, then sign in.
MCP Clients
Claude Desktop
Settings → Connectors → add custom connector (name zerno, URL https://zerno.one/mcp)
Cursor
Settings → MCP → Add server → URL https://zerno.one/mcp
