ScreenJournal

Connecting AI Tools (MCP)

Screen Journal ships an MCP (Model Context Protocol) server, so AI assistants you already use — Claude, or any MCP-enabled tool — can query your team's work record directly: what people worked on, where the hours went, and how something was done. Every answer is scoped to exactly what your role can already see in the dashboard, and no more.

5.1 Server URL

Point any MCP client at:

https://mcp.screenjournal.ai/mcp

5.2 Connect from Claude Code

  1. Add the server (--scope user makes it available in all your projects, not just the current folder):

    claude mcp add --transport http --scope user screenjournal https://mcp.screenjournal.ai/mcp

  2. Start a fresh Claude Code session so it picks up the new server, then run /mcp, select screenjournal, and choose Authenticate. Sign in and approve in the browser that opens — your login is stored securely and refreshes automatically.

  3. Run /mcp again to confirm the server shows as connected, then chat normally — try "Using ScreenJournal MCP, what am I working on today?" and approve the tool the first time it's used.

5.3 Connect from Claude Desktop or claude.ai

Go to Settings → Connectors → Add custom connector, paste the server URL above, and complete the sign-in when your browser opens.

5.4 Other MCP clients

Any client that supports remote MCP servers over streamable HTTP with OAuth works the same way: add the server URL and complete the browser sign-in.

5.5 Authorisation and permissions

Connecting opens Screen Journal's consent screen in your browser — sign in with your normal account and approve the client. If you see an access error, your organisation restricts which members may connect MCP clients; ask your admin to add you. Once connected, queries run under the same role permissions as the app: you can never see more through MCP than you can in Screen Journal itself.