Worknano

MCP: your AI apps, working inside Worknano

Updated 2026-10-15

You already ask an AI app to plan your week, draft a brief or untangle a project. Then you copy the answer back into the tools where the work actually lives. MCP removes that step. Every Worknano workspace runs an MCP server, so Claude, Claude Code, Cursor, Codex and Gemini CLI can work directly with your projects, tasks, OKRs, deals and files.

What changes when your AI app can see your work

Your permissions, not a master key

Each person connects with a personal key, so the app works as that person. Every call is checked against three things: what the workspace allows over MCP, what that connection may touch, and the person's own role. If you cannot see a record in Worknano, your AI app cannot see it either. Secrets, users, roles and integration settings are never exposed, and deleting records is off by default.

Under your control

One workspace, any AI app

Worknano gives every module the same interface, the same data and the same permissions, and you shape it with AI instead of a development project. MCP extends that to the AI tools your team already likes. Developers keep Cursor or Claude Code, managers keep the Claude app, and everyone works on the same records. Teams that prefer to stay inside Worknano get the same help from the built-in AI assistants and agents.

Get started

An admin switches on Enable MCP Server in Organization → Settings. Each person then clicks Connect in My → Integrations and pastes the Server URL and key into their app. The full steps, with ready-to-paste examples, are in the MCP setup guide. To connect Worknano to other software instead, see Integrations.

[FAQ-CATEGORY:integrations]