MCP server

Work on your projects from your AI agent

NUSK has a built-in Model Context Protocol (MCP) server. Connect Claude Code, Codex, Cursor or any other MCP client, then ask it to find your work, create tasks, update status or log risks without leaving your editor.

Set it up in two minutes Create a free workspace

What your agent can do

Nothing to install. Your agent connects to your workspace over HTTPS and acts as you, with your project permissions.

Find work

List your projects, see your open work across all of them, search and filter work items, and read an item in full with its comments.

Plan

Create work items, change status, owner, priority, dates and estimates, and move items between sprints and the backlog.

Collaborate

Comment on work items and turn meeting action items into tasks.

Track risk

Read the RAID log and sprint progress, and add new risks.

Set it up

  1. Create a token. Sign in to your workspace, open Profile → API tokens and create a token. Choose Read only if the agent should only look, or Read and write to let it make changes.
  2. Copy your server URL. It is your workspace address followed by /api/mcp, for example https://nusk.dev/your-workspace/api/mcp. The API tokens page shows it ready to copy.
  3. Add it to your agent using one of the snippets below. Replace your-workspace and nusk_... with your own values.

Claude Code

Run this once in a terminal.

claude mcp add --transport http nuskpm https://nusk.dev/your-workspace/api/mcp --header "Authorization: Bearer nusk_..."

Codex

Add this to ~/.codex/config.toml, then set NUSKPM_TOKEN to your token in your shell.

[mcp_servers.nuskpm]
url = "https://nusk.dev/your-workspace/api/mcp"
bearer_token_env_var = "NUSKPM_TOKEN"

Cursor, Windsurf and other MCP clients

Add this to the client's MCP configuration file, for example .cursor/mcp.json.

{
  "mcpServers": {
    "nuskpm": {
      "url": "https://nusk.dev/your-workspace/api/mcp",
      "headers": { "Authorization": "Bearer nusk_..." }
    }
  }
}

Then ask your agent something like “What's on my plate in NUSK this week?” or “Create a task in project AB to add a logout button and assign it to me.”

Safe by design

The agent can never do more than you can.

  • Your permissions — every request is checked against your role in each project.
  • Read-only tokens — a read-only token only exposes the read tools.
  • You approve changes — MCP clients ask you before each tool call that changes data.
  • Full history — changes made by an agent are marked “via AI agent (MCP)” in revision history and can be reverted.
  • Revoke any time — delete the token in Profile → API tokens and the agent loses access at once. Tokens can also expire automatically.

Questions

Do I need to download anything?

No. The MCP server is part of every NUSK workspace. You only add its address and your token to your agent.

Does it work with the self-hosted edition?

Yes. Use your own server's address followed by /api/mcp, for example https://pm.example.com/api/mcp.

Can I add it to claude.ai or ChatGPT on the web?

Not yet. Those apps need a one-click sign-in flow, which is coming next. Today it works with clients that accept a server URL and a token header, such as Claude Code, Codex, Cursor, VS Code and Windsurf.

Is my data sent to the AI provider?

Only what your agent reads through the tools you allow, and only to the AI provider your agent already uses.