MCP Documentation

Remnus MCP is a Model Context Protocol server built into every Remnus workspace. It lets AI agents — Claude, Cursor, Windsurf, and any MCP-compatible client — read and write your workspace data over a standard HTTP API.

What you can do

• Query pages and databases with full-text search and property filters
• Create and update pages, database rows, and entire databases
• Automate reports, task extraction, and kanban triage with built-in prompts
• Monitor all agent activity through a structured audit log

Endpoint

https://remnus.com/api/mcp

Supports both Streamable HTTP (stateless, one request per call) and SSE (stateful, persistent connection).

Quick start

1. Open your workspace → ⋯ menu → Settings → Tokens tab
2. Click New Token, choose a name and scope
3. Copy the token and configure your AI client — see Getting Started

Documentation

Getting Started	Token setup, Claude Desktop config, first call
Connect Your Editor	Windsurf, Cline, Zed & more — ready configs + OAuth
Authentication	Bearer tokens, scopes, rate limits
Read Tools	7 read-only tools
Write Tools	7 write tools
Resources	4 MCP resource templates
Prompts	5 built-in prompt templates