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
Eng Director + HR Lead · ClaudeLive Assistant · Scoped OAuth
Prompt

Sprint 8 velocity cratered vs Sprint 7. Was it the team or our capacity, and when can we safely ship 2.4?

Live RecordsearchJiraIssuesUsingJql
33 pts committed, 18 done (55%) · S7 was 39/41 (95%)
Inspect query parameters{ "jql": "sprint = 'Sprint 8' AND project = PAY" }
Live Recordlist_pull_requests
median time to merge 71h vs 19h in S7 · 6 PRs open >4d
Inspect query parameters{ "owner": "acme", "repo": "payments", "state": "all" }
Live Recordget_team_availability
5/9 absent some days · Maya+Tomas+Lena overlap May 25 to 29
Inspect query parameters{ "teamId": "team_pay", "startDate": "2026-05-18", "endDate": "2026-05-31" }
Live Recordget_coverage_risks
team_pay HIGH May 26 to 28 · 4/9 out, 2 senior reviewers
Inspect query parameters{ "startDate": "2026-05-18", "endDate": "2026-06-05" }
Live Recordget_team_time_summary
Raj 94h logged / 76h expected (+18h) · 3 others <70%
Inspect query parameters{ "teamId": "team_pay", "startDate": "2026-05-18", "endDate": "2026-05-31" }
Sprint 8 looks like a coverage problem, not slow work. Maya, Tomas and Lena overlapped on leave (May 25–29), review capacity dropped hard, and PRs sat for days. First realistic ship date for 2.4 is June 4 once reviewers are back. Worth checking in on Raj - he logged +18h that week.
Every tool shown ships in the product

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, 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 Anna'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 Jane Doe, 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.”

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.”

160+ 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.

Eng Director + HR Lead · ClaudeLive Assistant · Scoped OAuth
Prompt

Sprint 8 velocity cratered vs Sprint 7. Was it the team or our capacity, and when can we safely ship 2.4?

Live RecordsearchJiraIssuesUsingJql
33 pts committed, 18 done (55%) · S7 was 39/41 (95%)
Inspect query parameters{ "jql": "sprint = 'Sprint 8' AND project = PAY" }
Live Recordlist_pull_requests
median time to merge 71h vs 19h in S7 · 6 PRs open >4d
Inspect query parameters{ "owner": "acme", "repo": "payments", "state": "all" }
Live Recordget_team_availability
5/9 absent some days · Maya+Tomas+Lena overlap May 25 to 29
Inspect query parameters{ "teamId": "team_pay", "startDate": "2026-05-18", "endDate": "2026-05-31" }
Live Recordget_coverage_risks
team_pay HIGH May 26 to 28 · 4/9 out, 2 senior reviewers
Inspect query parameters{ "startDate": "2026-05-18", "endDate": "2026-06-05" }
Live Recordget_team_time_summary
Raj 94h logged / 76h expected (+18h) · 3 others <70%
Inspect query parameters{ "teamId": "team_pay", "startDate": "2026-05-18", "endDate": "2026-05-31" }
Sprint 8 looks like a coverage problem, not slow work. Maya, Tomas and Lena overlapped on leave (May 25–29), review capacity dropped hard, and PRs sat for days. First realistic ship date for 2.4 is June 4 once reviewers are back. Worth checking in on Raj - he logged +18h that week.
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).

Shows work before it mutates

Before booking or changing records, the assistant lays out the plan so a human can say yes or no.

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.

When you're ready

Connect your assistant

Already evaluating? One endpoint and OAuth sign-in. Works with any client that speaks Model Context Protocol.

MCP endpointhttps://app.squadbear.com/mcp
Full setup guideCopy master setup prompt

One command in your terminal. Authenticate once, then ask.

  1. Run the command below in your project terminal.
  2. Start claude, open /mcp, choose squadbear, and Authenticate.
  3. Complete the browser sign-in, then ask whoami to confirm the connection.
Terminal
claude mcp add --transport http squadbear https://app.squadbear.com/mcp

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, it shows its work before acting, and everything it does is recorded 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/ATS and no performance-review product. Connected assistants don't rank candidates, score employees for promotion or termination, or auto-trigger people decisions. They fetch data, draft admin and file what a human already has permission to do.

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, team health 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 and cover takes care of itself, 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 →

From the blog

Practical guides on this part of the job, written for teams small enough that the person reading this is also the person doing it.

Slack Leave Approvals: Why Approving in Slack Beats Email

Why leave approvals stall in email, and how Slack DMs with Approve and Reject buttons cut the wait to seconds while the HR system stays the record.

Read the guide →

EU AI Act in HR: What You Can & Cannot Automate

Emotion recognition at work is banned, high-risk HR duties slipped to December 2027, and everyday drafting is fine. The EU AI Act tiers, sorted for HR.

Read the guide →

Routing HR Questions Through an AI Assistant: What Broke

We routed our HR questions through an AI assistant wired to our own system. What worked, the five ways it broke, and what stays human.

Read the guide →

Browse all guides

Less admin. More of the actual job.

Try the live demo - three ready-made sign-ins, real data, nothing to set up. Or start free in minutes.

Start freeTry the live demo