ZERNO Lite MCP Server
OfficialZERNO Lite — MCP Server
Official metadata for the ZERNO Lite Model Context Protocol (MCP) server.
ZERNO Lite is a remote MCP server that connects AI agents to ZERNO project context — project briefs, task and agent context, and structured intake workflows — over a secure, OAuth-authorized endpoint. It's built for coding agents, product agents, and automation workflows that need to understand a project before acting, without unrestricted backend access.
This repository is the public "front door" for the hosted server: metadata,
server.json, and the tool catalog for MCP directories. It does not contain the backend source — the server runs as a hosted service at the endpoint below.
Endpoint
https://zerno.one/mcpTransport | Streamable HTTP (JSON-RPC 2.0 over POST) |
Auth | OAuth 2.1 with PKCE (S256); bearer tokens; per-project authorization |
Registration | Dynamic Client Registration (RFC 7591) — no static API key |
Capabilities | 8 tools · 0 resources · 0 prompts |
Registry name |
|
Manifest |
Related MCP server: mcp-devtools
Quickstart
Add a remote connector named zerno with URL https://zerno.one/mcp, then complete the OAuth
consent in the browser.
Claude Code / Claude Desktop: Settings → Connectors → add custom connector (name
zerno, URL above).Codex CLI:
codex mcp add zerno --url https://zerno.one/mcpCursor: Settings → MCP → Add server → URL
https://zerno.one/mcp
For user-scoped tokens, tell the agent which project with a project_slug (e.g. zerno-one).
Tools (8)
Tool | Does | Writes? |
| Project orientation: focus, next action, do-not-do, memory index | no |
| Compiled project memory + recent events for an agent run | no |
| Filtered backlog listing | no |
| Full detail for one task | no |
| Patch task fields/status (ICE recomputed) | mutates |
| Submit triage proposals (pending human approval) | creates proposals |
| File a review task from an agent report | creates a task |
| Append a session summary to project memory | creates memory event |
Full machine-readable schemas: tools-list.json. No tool deletes data or calls
third-party services. tools/list is scope-filtered — a read-only token sees only the four read tools.
Security & privacy
Every call requires OAuth; nothing is exposed unauthenticated. Bearer tokens are hashed at rest, no secrets are returned in tool output, and every call is audit-logged. Access is tied to the user's authorized ZERNO workspace/project.
Limitations
Requires a ZERNO account and an authorized project. Remote/hosted only (no stdio or packaged distribution). Tools only — no MCP resources or prompts.
Files in this repo
server.json— Official MCP Registry manifesttools-list.json— fulltools/list(8 tools, exact schemas)smithery-server-card.json— static server card for SmitheryLICENSE— MIT
Links
Website: https://zerno.one
License
MIT — applies to this metadata repository.
This server cannot be deployed
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Remote MCP server to read and manage your Atako AI agents, messages, files, and integrations.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Remote MCP server for The Colony — a social network for AI agents (posts, DMs, search, marketplace).
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA secure and pluggable MCP server to run terminal commands on your local machine or cloud server — remotely, safely, and with LLMs or agentic clients.-
- AlicenseBqualityDmaintenanceProduction-grade MCP server that gives AI agents safe access to your local dev environment: filesystem, databases, processes, and OpenAPI specs.15263MIT
- AlicenseBqualityAmaintenanceA secure MCP server for shell operations, terminal management, and process control, enabling AI assistants to safely execute commands and manage interactive sessions.137046MIT
- FlicenseNot gradedqualityDmaintenanceA modular MCP server that provides AI agents with cognitive memory, local system access, and secure remote execution capabilities through three integrated layers (Brain, Master, Remote).-