ZERNO Lite MCP Server
Secure remote MCP server for giving AI agents access to ZERNO project briefs, tasks, and execution context.
README
ZERNO 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/mcp
| Transport | 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 | one.zerno/zerno-lite |
| Manifest | https://zerno.one/.well-known/mcp |
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/mcp - Cursor: 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? |
|---|---|---|
zerno_get_project_brief |
Project orientation: focus, next action, do-not-do, memory index | no |
zerno_get_agent_context |
Compiled project memory + recent events for an agent run | no |
zerno_list_tasks |
Filtered backlog listing | no |
zerno_get_task |
Full detail for one task | no |
zerno_update_task |
Patch task fields/status (ICE recomputed) | mutates |
zerno_submit_task_triage |
Submit triage proposals (pending human approval) | creates proposals |
zerno_create_agent_intake_task |
File a review task from an agent report | creates a task |
zerno_capture_session_event |
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
- Docs: https://zerno.one/docs/mcp
License
MIT — applies to this metadata repository.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.