Platform · EU hosted

The authority layer for agentic AI. One rulebook, one record, every agent.

Agents are eager. TapPass sits at the boundary between your agents and the models and tools they use, decides every call against rules you own, and keeps a signed record of what happened. On the stack you already run.

✓Free for one person · no credit card

People and agents
PAProcurement agent
Claude Code
CCCustomer care
LPLies Peeters, finance
TapPassobserve · decide · record
✓Observe · Procurement agent, for Pieter Vosidentity
!Decide · PUR-1 holds €1,840.00 for Liesrules
✓Route · IBAN redacted, Mistral Large, EUdata
✓Record · signed, chained, replayablerecord
Models and tools
Mistral
OpenAI
Anthropic
MCP · GitHub, Slack, banking
01Four ways in

Enforce in the path, or from your own code. Same rules either way.

Pick the entry point that fits each team. They all decide against the same rulebook and write to the same record.

02How it fits together

Three promises hold everywhere. Whichever way a call comes in.

01One rulebook

Written once, in plain words, and applied to every agent and framework: LangChain, CrewAI, MCP, Claude Code and your own agents. No rule copied into each team’s code.

PUR-1 · Purchase approvals WHEN intent = move money AND amount > 1,000 EUR THEN hold for an approver
02One signed record

Every allow, hold and block from the gateway, the MCP gateway and the Verdict API lands in the same record. Signed, chained to the one before, and yours to export.

09:41:44 hold pay €1,840.00 09:43:02 signed Lies Peeters, passkey 09:43:03 allow chain verified
03Deterministic and replayable

A model never makes the call. The verdict comes from your rules and the facts, the same way every time. Replay any decision to prove it, or a draft rule over last week.

replay dec_7Hq2Lm rules PUR-1 v3 result needs_approval ✓ identical
In the pathGateway and MCP gateway
  • ✓Repoint one base URL, nothing rebuilt
  • ✓Redaction and EU routing before a model sees a thing
  • ✓Per-tool permissions on every MCP server
From your own codeVerdict API
  • ✓Your traffic keeps its current path
  • ✓Fail closed or fail open, per integration
  • ✓Mix with the gateway, team by team
03What it does

Observe. Decide. Record. On every call.

Most of the value will come from agents calling other agents, tools and models across teams and companies. That only works if every call is governed.

Full visibilityEvery prompt, response and tool call in real time, per agent, person and team.live
Least privilegeEach agent gets the tools its job needs. Authority is earned from watched behaviour, not handed over on day one.per tool
A person on what mattersPayments, deletes and exports wait for a named approver, who signs with a passkey. Nobody approves their own request.passkeysfour eyes
Redaction and EU routingPersonal data and secrets removed in transit. Prompts with personal data go only to EU-hosted models.never stored raw
Your keys, in a vaultBring your own model keys. They stay encrypted in a vault, never on people’s laptops.BYOK
Evidence is a queryReports turn the record into evidence packs, and every decision streams to your SIEM as OpenTelemetry.EU AI ActGDPR
04Where it runs

Three ways to deploy. One rulebook.

Start in our EU cloud in minutes. Move into your own environment when procurement asks.

TapPass cloudEU hosted, live in minutes

We run it for you in a European region. The fastest start, with a DPA on request.

Your tenancyInside your own cloud

For Enterprise: TapPass runs in your own environment, under your own controls.

On-premisesOn your own servers

Signed images and a signed licence. Air-gapped deployments on request, with our team.

05Get started

See it work first. Then decide what it costs.

Questions

The platform, in plain answers.

Something else on your mind? Talk to our team.

Which part of TapPass do we need?

Most teams start with the gateway: repoint one base URL and every model and MCP tool call passes your rules. Add the MCP gateway for per-tool permissions, or call the Verdict API where you would rather enforce inside your own code. All of them share the same rules and the same record.

Is a model making the decisions?

No. Your rules compile to deterministic logic. The same facts give the same verdict every time, and you can replay any decision on the record to prove it.

Where does TapPass run?

In the EU, in our cloud. Enterprise customers can run it in their own tenancy or on their own servers.

How long does it take to start?

Minutes for one agent: point the base URL at TapPass and watch. Nothing is blocked until you switch a rule to enforcing.

What does it cost?

Free for one person, with the whole product and no time limit. Team and Enterprise are quoted.

One rulebook for every agent. Start with the one you run today.

Connect one agent and see every call TapPass would have held, stopped or routed elsewhere. Nothing is blocked while you learn.

✓ Free for one person✓ No credit cardBacked by Start it @KBCVLAIO✓ EU hosted✓ Built in Belgium✓ Your own model keys✓ Encrypted at rest and in transit✓ DPA on request