EnglishENPolskiPLDeutschDEEspañolESBahasa IndonesiaID
Start free
Model Context Protocol

Run HR from the AI you already use

SquadBear is the system of record. Claude, ChatGPT, Cursor or any MCP assistant does the talking under that person's login. Book leave, check who's free, log time, pull a report. Draft, fetch and file. Never a verdict about a person.

Start freeExplore in demo
Head of People · ClaudeExample workflow
Prompt

Require that carried Standard vacation days start by the end of September.

Sample recordupdate_leave_policy
approvalRequired · reviewUrl /agents?approval=… · 30 min · nothing changed
Inspect query parameters{ "policyId": "pol_vacation", "carryoverDeadlineKind": "mustBeTakenBy", "carryoverDeadlineMonths": 9 }
Sample recordget_approval_status
approved · canCommit true · same arguments only
Inspect query parameters{ "approvalId": "plan_vacation_carryover" }
Sample recordupdate_leave_policy
policy version 2 published · enrolled employees keep their current balances
Inspect query parameters{ "policyId": "pol_vacation", "carryoverDeadlineKind": "mustBeTakenBy", "carryoverDeadlineMonths": 9, "approvalId": "plan_vacation_carryover" }
Done, but not from the chat token. You approved the exact proposal in SquadBear, then I committed it. Carried Standard vacation must now start by 30 September of the following year; unused days stay bookable after that.
Every tool shown ships in the product

Connect your assistant in one click

Claude, Cursor, or VS Code. The button opens that app with SquadBear filled in. You confirm, then sign in once. No API key.

Claude

Opens claude.ai with the name and URL filled in. Nothing is added until you confirm. A free account can add one custom connector.

Add to Claude
Cursor

Opens Cursor’s install prompt. Confirm there, then sign in.

Add to Cursor
VS Code

Opens VS Code’s install prompt. Confirm there, then sign in.

Add to VS Code

Custom connector on plans that support connectors (Plus, Pro, Team, or Enterprise). SquadBear is not in the ChatGPT plugin directory, so paste this URL. It is not the same endpoint as the other clients.

  1. In ChatGPT, open Settings → Connectors and add a custom MCP connector.
  2. Paste the ChatGPT endpoint below.
  3. Sign in to SquadBear, approve scopes, and start asking.
ChatGPT MCP URL
https://app.squadbear.com/mcp/chatgpt
Ask your agent

Copy and send this to your agent

Paste this into the agent. It follows the official setup guide and runs the commands. You only complete the browser sign-in.

Claude Code
Set up SquadBear so I can run HR from this session.
1. Read https://squadbear.com/agent-setup/prompt.md and follow the Claude Code section. Run the commands yourself. Only the browser sign-in is mine.
2. Register the server: `claude mcp add --transport http squadbear https://app.squadbear.com/mcp`
3. Start claude, run /mcp, choose squadbear, and Authenticate. Tell me when the browser is open.
4. After I approve scopes, call get_context and confirm the connection is me.
MCP endpointhttps://app.squadbear.com/mcp
Full setup guide

Why teams pick it

Scale HR without scaling headcount

The repetitive admin quietly handles itself.

Hours back, every week

The HR queue stops being everyone's bottleneck.

Fewer mistakes, more trust

The system does the math and applies the rules. Humans keep the judgment.

Works with what you already use

Your team's existing AI assistant. Not another login.

Use cases

What teams ask every week

Real HR work in plain language. Not generic “create record” wrappers: domain tools for leave, time, attendance, health, performance, processes and admin, with the same rules as the web app.

Leave & coverage

Balances, policy-aware requests, substitutes, coverage risk and team calendars.

  • “How many vacation days do I have left?”
  • “Book next Friday off and check coverage first.”

Approvals

Inbox, approve or reject under the same role permissions as the UI.

  • “What's in my approval inbox?”
  • “Approve Mila's leave if coverage looks fine.”

Time tracking

Leave-aware timesheets, projects, Jira/Linear/GitHub-linked work items.

  • “Log 2 hours on PROJ-123 yesterday.”
  • “Summarise my timesheet this week.”

Attendance

Clock in/out and presence without switching apps.

  • “Clock me in.”
  • “Who is present on my team right now?”

Team health & retros

Pulse runs, eNPS, trends and retrospective sessions with follow-through actions.

  • “Start a Pulse 5 health check for Platform, keep it anonymous.”
  • “Summarise the last health run for Engineering.”

Processes & documents

Onboarding/offboarding checklists, policy acknowledgments and files.

  • “Start onboarding for Emily Saputra, start date next Monday.”
  • “Who hasn't signed the remote-work policy?”

Reports

Absence summaries, PTO liability, Bradford factor and audit-friendly exports.

  • “Bradford factor for Engineering this quarter.”
  • “PTO liability by team for month close.”

Performance and goals

Draft a review the author submits. Goals freeze when the round opens. Peer answers arrive as Peer 1, with no name. The assistant cannot submit or read upward feedback.

  • “Draft my manager review for Maya's Q4 round. I pick every rating.”
  • “Which goals were frozen when this round opened?”

Admin (role-gated)

Invites, policies, modules and workspace setup, but only if you could do it in the app.

  • “Invite alex@company.com as a manager.”
  • “Walk me through workspace setup with get_setup_status.”

210 tools in the catalog. Same surface as the UI and /api/v1.

Act, don’t just answer

MCP is not a vendor chatbot

RAG and in-app AI read documents. MCP lets the assistant you already use operate live HR under your login.

Vendor chatbot / RAG

  • Explains the handbook, doesn't book leave
  • Lives only in the vendor’s UI
  • Often a shared service account
  • Shallow API wrappers via Zapier

SquadBear MCP

  • Books leave under your real policy
  • Works in Claude, ChatGPT, Cursor, Codex…
  • User OAuth: acts as you, with your role
  • Domain tools: coverage, Bradford, health, processes
See it in action

Real tool calls, not a mock chatbot

Every tool in these demos ships in the product: leave, Jira-linked time, health and more.

Head of People · ClaudeExample workflow
Prompt

Require that carried Standard vacation days start by the end of September.

Sample recordupdate_leave_policy
approvalRequired · reviewUrl /agents?approval=… · 30 min · nothing changed
Inspect query parameters{ "policyId": "pol_vacation", "carryoverDeadlineKind": "mustBeTakenBy", "carryoverDeadlineMonths": 9 }
Sample recordget_approval_status
approved · canCommit true · same arguments only
Inspect query parameters{ "approvalId": "plan_vacation_carryover" }
Sample recordupdate_leave_policy
policy version 2 published · enrolled employees keep their current balances
Inspect query parameters{ "policyId": "pol_vacation", "carryoverDeadlineKind": "mustBeTakenBy", "carryoverDeadlineMonths": 9, "approvalId": "plan_vacation_carryover" }
Done, but not from the chat token. You approved the exact proposal in SquadBear, then I committed it. Carried Standard vacation must now start by 30 September of the following year; unused days stay bookable after that.
Every tool shown ships in the product
Security & control

Your permissions. Your audit trail.

Connecting an assistant to people data is serious. The protocol sets the floor; our implementation keeps HR-grade boundaries.

User OAuth, not a service account

Every session inherits the human who connected it. No shared bot principal that can see the whole company.

Scopes + roles

The agent can only do what that person could do in the web app (leave:read, time:write, health:write, and so on).

Sensitive changes wait in SquadBear

Everyday writes follow the assistant’s Ask setting. Leave policies and entitlements, workspace settings, role changes, admin invites, erasure and process starts store a 30-minute proposal. Only the same signed-in session can approve it; the MCP token cannot.

Same audit log as the UI

Every tool call lands in Admin → Audit with who asked, what ran, and when. Same path as REST and the panel.

Decision support, never a verdict

No emotion recognition, no hire/fire/promote automation, no ranking people for outcomes. Draft, fetch and file only.

Included on every plan

MCP is free on Free, Team and Enterprise. You pay for seats, never for the connector.

Questions, answered

What is Model Context Protocol (MCP)?

MCP is the open standard that lets AI assistants discover and call tools in external systems. SquadBear runs a first-party MCP server so Claude, ChatGPT, Cursor, Codex and other clients can operate leave, time, health and core HR under your permissions.

Do we need special software?

No. It works with the AI assistants your team already uses (Claude, ChatGPT and other MCP-capable clients). SquadBear is the system of record and the tool server. The third-party model does the language work.

Is it safe to let an assistant do this?

Yes. It can only do what the person could do anyway. Everyday writes follow the assistant's Ask setting. Sensitive changes prepare a 30-minute proposal that only the same person, signed in to SquadBear, can approve - the assistant's token cannot. That covers leave policies, leave types, allowances and presets, workspace settings, starting a process, erasing a person, and changing someone's role or status or granting admin access. Everything lands on the same audit trail as the web app. Sessions use user OAuth, not a shared service account.

Does it cost extra?

No. MCP is included on every plan, free ones too. You're never charged more for the connector. (Your AI provider's own plan rules still apply.)

What can people actually ask it to do?

The everyday admin: book or check leave, see who's covering, log time, set up a record after you've hired someone, chase a policy sign-off, pull a report. Same tasks they'd otherwise do by hand. Choose permission presets during authorization; specialist tasks use the same connection.

Will it just make things up?

No. The system does the calculations and applies your rules, so answers stay grounded in your real data, not guessed.

Can it detect emotions, mood or "engagement" from people?

No. Article 5 of the EU AI Act already bans AI that infers emotions of people at work. We don't offer emotion recognition, call sentiment scoring, webcam engagement or per-person mood inference. Team health is what people choose to answer on pulse checks and eNPS: self-reported, usually anonymous, never invented by a model watching them.

Can the AI decide who to hire, fire, promote or how someone performs?

No. SquadBear has no recruiting or ATS. Performance reviews are written by people (self, peer and manager). An assistant can save a draft the author edits and submits in SquadBear. It does not submit, share, score or rank anyone, and it does not hire, fire or promote.

Who is "the AI" here, SquadBear or Claude/ChatGPT?

The assistant is the third-party client your team connects (Claude, ChatGPT, etc.). SquadBear exposes MCP tools, enforces your roles and scopes, and logs every action. We don't run a separate black-box "HR brain" that judges people. We run the product the assistant operates under your rules.

One suite for the whole people-ops day

Leave, time, attendance, team health, performance reviews and the employee record work as one, so the picture is always joined up - a booked holiday is known everywhere, a new hire's day one starts itself, and a quiet team never slips through.

Leave management

Time off should be the easy part

When booking leave is effortless, people actually rest, managers stop firefighting, and you always know where the business stands.

Explore Leave management →
Time tracking

Know where the week actually went

Time tracking only matters when it's honest and effortless.

Explore Time tracking →
Attendance

Clock in. That's the whole job.

Four buttons for the day.

Explore Attendance →
Team health

Know how your team is really doing

Great teams quietly drift long before they visibly break.

Explore Team health →
Core HR

Day one, already handled

The moment someone is hired, their record exists, their onboarding tasks have owners and dates, and the policies that need signing find them by themselves.

Explore Core HR →
Performance

360 reviews people actually finish

One cycle says who is reviewed and which form they answer.

Explore Performance →

From the blog

Practical guides on policies, edge cases and rollouts - for HR leads, founders and managers running modern teams.

EU AI Act and Performance Reviews: What AI Must Never Decide

Annex III point 4(b) in plain language: why a composite score is a different object from a draft a human submits.

Read the guide →

Engineer Self-Reviews From GitHub and Jira, Without AI Slop

A worked engineering self-review: behavioral anchors, why pull-request counts are clues, and a draft that links the work you shipped.

Read the guide →

Mixed UoP and B2B Teams: Five Places Your HR Tool Blurs the Line

How software houses with employees and B2B contractors keep leave, hours, payroll exports and ISO 27001 policies in one workspace without blurring contracts.

Read the guide →

Browse all guides

Less admin. More time for people.

Let your assistant handle routine leave, time and HR admin. Make room for the conversations and support your team needs.

Start freeExplore example workflows
Your agent is connectedLeave · Time · People
SquadBear MCPReady to help