Can Claude / ChatGPT / Cursor use KI BMS directly?

Yes, via the MCP server. It's a stdio JSON-RPC server that wires into Claude Desktop, Cursor, or any MCP-aware client in five lines of config. The list of tools matches your data model 1:1 - whatever a CRUD type exposes in the UI is exposed identically to the agent.

Do agent calls share the same auth + access controls?

Yes. The MCP server authenticates with the same JWT or PAT a human session uses. Sharing rules, org membership, rate limits, suspicion bans - all of it applies. There's no "agent backdoor" that bypasses the access matrix.

Is there an audit trail for agent actions?

Yes. Every mutation goes through the same audit-log path as a UI click. The transport (UI / API / CLI / MCP) is recorded as channel metadata so you can filter "what did the agent do this hour" from your account history.

Can I rate-limit an agent separately from a human?

Per-token rate limits apply, so you can issue an agent its own PAT and cap it independently. The shared user-level bucket also caps total throughput, so a runaway loop can't drain your whole account. The CLI's auto-update channel marker means you can also see in audit which version is calling.

Does the MCP / API surface cost extra?

No. Same plan, same surface. We don't paywall the agent - it's the same product, the same schema, the same access gates. If a plan can do X in the UI, it can do X via MCP.

KI BMS

Pricing

Compare

KI BMS: the agent-friendly alternative to Factorial

Same product, same surface for humans and AI agents. MCP server + CLI + drop-in clients in 15 languages.

Agentic alternative

ATS

Comparison

HR suite

Julia YukovichCo-Founder + CEO

·April 16, 2026·

2 min read

KI BMS ships an MCP server you can wire into Claude Desktop or any MCP client in five lines. The same auth + access gates apply, the same audit log records every action, the same rate limits apply. Factorial doesn't currently expose this surface - that's the gap.

At a glance

Factorial is a strong pick if you want an HR platform for all personnel admin - time tracking, absence, documents, payroll handoff and a recruiting module on top. For 20-200-person companies without dedicated HR software, that's a sensible consolidation. KI BMS is right when recruiting is your bottleneck and you want KI pre-sort with reasoning, a real pipeline and a German careers page instead of a platform's generalist recruiting tab. The most common 2026 architecture: Factorial for HR admin, KI BMS for recruiting in parallel.

Agent surface

What 'agent-friendly' actually means in practice

KI BMS ships an MCP server, a CLI, and drop-in clients in 15 languages. They're auto-generated from the same schema your UI uses; the auth, the access gates, the rate limits, the audit log all apply identically whether you're clicking buttons or calling the API. Factorial doesn't currently expose this surface, which is the gap a serious agent integration trips over - the agent ends up scraping the UI through a browser, which is fragile, slow, and silently bypasses everything below.

KI BMS vs Factorial: agent-readiness comparison

	Ours KI BMS	Theirs Factorial
Time tracking + absence
Documents + payroll handoff
Recruiting module	Specialist	Module
KI fit-score with reasoning		KI features present, recruiting depth limited
Multi-voice scorecards		Limited
Careers page included		Basic page
GDPR auto-anonymisation		Manual
Hosted in Germany		EU hosting
Starting price	€0 / €1 / €10 per month	Per employee, module-dependent
Contract model	Monthly cancellation	Annual contract typical

When to pick which

Pick KI BMS when

Recruiting is your bottleneck - 5+ open roles or 100+ applications per quarter, and the generalist module no longer suffices.

You want KI pre-sort with reasoning and structured scorecards, not 'another recruiting tab in the platform'.

You already run Factorial (or another HR platform) and just need a better ATS alongside.

Pick Factorial when

You don't have HR software yet and want to consolidate time tracking, absence, documents and payroll handoff first.

Recruiting is small - 1-4 roles a year, the module needs to suffice, not shine.

A single platform is politically easier to procure than two specialists.

Agentic-integration questions

What an agent-builder asks before wiring a tool into Claude / ChatGPT / Cursor.

Start with KI BMS

Free plan, no credit card. We host in Germany. Export + delete are self-serve.

Written by

Julia Yukovich

Co-Founder + CEO

Julia is one of the Co-Founders. She handles design, product direction, and most of the support replies that arrive in the morning.

julia.yukovich at aicuflow dot comLinkedIn