Use SquadBear from Claude - the MCP integration

Connect Claude to SquadBear over MCP and run leave, time, team health and core HR in plain language, with your own permissions.

SquadBear ships a built-in MCP server, so Claude can read and act on your workspace in plain language, using your login and your permissions. Nothing new to install. Add SquadBear as a custom connector and start asking.

What you can do in Claude

Anything you could click in the app, you can ask Claude to do instead. Book and check leave, log time, run a health check, manage records, start a joiner process after you've hired someone, chase a handbook signature. It is the same permission model as the UI, so the answer is your real data. Claude runs the calculation. It does not guess.

What it does not do: emotion or mood inference, candidate screening, ranking people for hire / fire / promote, or automatic people decisions off a score. Claude is the assistant. SquadBear is the system of record and the permission boundary.

Ask it to call whoami first. It should come back with your role, manager, teams and holiday calendar. Proof the connection resolved to you before you hand it anything real. It also returns toolGating: how many tools this session can see, and how many are hidden by role, a disabled module, the plan, or a scope you did not grant.

How to connect

1. Your MCP endpoint is https://app.squadbear.com/mcp. The in-app Connect an agent page shows the same URL for the origin you opened, with copy-ready snippets for Claude Code and Gemini CLI.
2. In claude.ai or the Claude desktop app, open Settings → Connectors → Add custom connector (custom connectors need a paid Claude plan). Name it "SquadBear" and paste the endpoint.
3. Claude opens the SquadBear sign-in. Log in, then choose which scopes the connection may use. The default covers leave and the directory. Approvals, admin, processes, time and health are separate ticks. A call that needs an ungranted scope comes back 403 insufficient_scope naming it.
4. In any chat, enable SquadBear under the search and tools menu, and start asking.

The full walkthrough, with the scope list and a worked example, is in Connect Claude to SquadBear.

Permissions, scopes and the audit trail

The agent acts as you, with your role's permissions, nothing more. The scopes you approve are frozen into that connection. Every action Claude takes is written to the same audit log as the web app and the REST API, at Workspace settings → Audit log. The UI, the API and the assistant all go through one permission and audit path. An agent is never a back door.

Logging hours needs time:write and Time tracking on. Opening a health check needs health:write and Team health on.

Prompts to try

Related

• Connect Claude to SquadBear
• Prompts to run through your connected agent
• Use SquadBear from ChatGPT