Skip to main content
skcal exposes a remote Model Context Protocol server so AI clients can log and query your data. It uses Streamable HTTP and is guarded by OAuth 2.1 — you sign in once in the browser to authorize, with no token to copy or paste.
Server URL: https://app.skcal.fit/mcp

​
Claude Code

Then run any skcal request in Claude Code; the first call opens a browser to authorize.

​
Claude (desktop & claude.ai)

1

Open connector settings

Open Settings → Connectors and click Add custom connector.
2

Paste the URL

Enter https://app.skcal.fit/mcp and save.
3

Authorize

Connect and sign in with your skcal account when prompted.

​
ChatGPT

1

Enable Developer mode

Open Settings → Connectors → Advanced, and turn on Developer mode. (Requires a paid plan.)
2

Add the server

Click Add custom connector and enter https://app.skcal.fit/mcp.
3

Authorize

Sign in with your skcal account to grant access.
Claude and ChatGPT don’t support a one-click install link for custom connectors yet — the links above open the connector settings, then you paste the URL. Claude Code (the command above) installs directly.
You can also open the skcal web app, tap Install MCP in the sidebar, and copy these instructions with the correct URL for your deployment.

​
Available tools

​
How authorization works

The server advertises OAuth discovery at /.well-known/oauth-authorization-server and /.well-known/oauth-protected-resource. Clients register dynamically, run the PKCE authorization-code flow against your skcal login, and receive a token scoped to your account — the same login used by the web app and CLI.