Model Context Protocol

Jalankan operasional HR dari AI yang sudah Anda gunakan

SquadBear adalah sistem data terpercaya. Claude, ChatGPT, Cursor, atau asisten MCP mana pun berinteraksi menggunakan kredensial orang yang menghubungkannya. Ajukan cuti, periksa siapa yang senggang, catat waktu kerja, dan tarik laporan. Membuat draf, mengambil data, dan menyimpan berkas. Tidak pernah membuat vonis atas manusia.

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

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.
Setiap alat yang ditampilkan tersedia langsung di dalam produk

Mengapa tim memilih SquadBear

Skalakan HR tanpa menambah beban staf

Administrasi rutin terselesaikan secara otomatis tanpa kerumitan.

Hemat jam kerja berharga setiap minggu

Antrean pertanyaan ke HR berhenti menjadi hambatan bagi seluruh tim.

Minim kesalahan, tingkatkan kepercayaan

Sistem melakukan kalkulasi dan menerapkan aturan. Pertimbangan tetap di tangan manusia.

Bekerja dengan alat yang sudah Anda gunakan

Asisten AI tim Anda yang sudah ada. Tanpa perlu kredensial login baru.

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
Instruksi

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.
Setiap alat yang ditampilkan tersedia langsung di dalam produk
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

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

Pertanyaan yang sering diajukan

Apa itu Model Context Protocol (MCP)?

MCP adalah standar terbuka yang memungkinkan asisten AI menemukan dan memanggil tools di sistem eksternal. SquadBear mengoperasikan server MCP resmi agar Claude, ChatGPT, Cursor, Codex, dan klien lainnya dapat mengelola cuti, waktu kerja, kesehatan tim, dan core HR sesuai izin akses Anda.

Apakah kami memerlukan instalasi software khusus?

Tidak. Bekerja langsung dengan asisten AI yang sudah digunakan tim Anda (Claude, ChatGPT, dan klien kompatibel MCP lainnya). SquadBear bertindak sebagai sistem pencatatan data dan penyedia tools. Model AI eksternal menangani pemahaman bahasa.

Apakah aman mengizinkan asisten AI melakukan tugas ini?

Ya. Asisten hanya dapat melakukan apa yang diizinkan untuk pengguna tersebut, menampilkan pratinjau tindakan sebelum mengeksekusinya, dan setiap aksi dicatat pada jejak audit yang sama seperti di aplikasi web. Sesi menggunakan OAuth pengguna individu, bukan akun bot bersama.

Apakah fitur MCP memerlukan biaya tambahan?

Tidak. MCP sudah termasuk di setiap paket, termasuk paket gratis. Kami tidak memungut biaya tambahan untuk konektor ini. (Ketentuan paket dari penyedia AI Anda tetap berlaku secara independen.)

Tugas apa saja yang dapat dijalankan lewat asisten AI?

Administrasi harian: mengajukan atau memeriksa saldo cuti, mencari rekan pengganti, mencatat jam kerja, membuat profil karyawan baru setelah rekrutmen, menindaklanjuti tanda tangan dokumen, dan menarik laporan. Tugas yang sama yang biasanya dilakukan manual – dengan lebih dari 160 tools di seluruh modul.

Apakah asisten AI akan mengarang data (halusinasi)?

Tidak. Sistem SquadBear yang melakukan penghitungan dan menerapkan aturan Anda, sehingga jawaban asisten selalu berakar pada data nyata perusahaan, bukan hasil tebakan.

Dapatkah sistem mendeteksi emosi, suasana hati, atau tingkat keterlibatan karyawan?

Tidak. Pasal 5 EU AI Act secara tegas melarang AI yang menyimpulkan emosi orang di tempat kerja. Kami tidak menyediakan analisis emosi, skor sentimen panggilan telepon, pantauan webcam, maupun kesimpulan suasana hati individu. Kesehatan tim hanya bersumber dari jawaban sukarela karyawan dalam survei pulse dan eNPS: dilaporkan mandiri, mayoritas anonim, dan tidak pernah direkayasa oleh model yang mengawasi mereka.

Bisakah AI memutuskan siapa yang direkrut, dipecat, dipromosikan, atau menilai performa?

Tidak. SquadBear tidak memiliki modul rekrutmen/ATS dan tidak memiliki sistem evaluasi performa karyawan. Asisten yang terhubung tidak menyortir kandidat, tidak memberi nilai untuk promosi/pemecatan, dan tidak memicu keputusan personalia otomatis. Asisten hanya mengambil data, menyusun draf, dan mencatat apa yang sudah diizinkan oleh pengguna manusia.

Siapa «AI» di sini: SquadBear atau Claude/ChatGPT?

Asisten adalah klien pihak ketiga yang dihubungkan tim Anda (Claude, ChatGPT, dll.). SquadBear menyediakan tools MCP, menegakkan peran dan batasan akses Anda, serta mencatat setiap aksi. Kami tidak menjalankan kotak hitam tersendiri yang menghakimi manusia; kami menyediakan produk andal yang dioperasikan asisten sesuai aturan Anda.

Kurangi beban administrasi. Fokus pada pekerjaan utama.

Coba demo interaktif langsung dengan data nyata tanpa perlu registrasi, atau mulai gratis dalam hitungan menit.