Controlling and enforcing access to APIs and network-accessible MCP capabilities, with authentication, policies, least-privilege tool exposure, scopes and runtime controls.
Tyk × Venedy · Wiesn Breakfast
AI Governance
in Action.
AI governance, API security and a Bretzel.
How to control and continuously validate what AI agents can actually access, change and trigger through APIs and MCP.
The central question
What can an AI agent access, change and trigger?
Under whose authority and in which context? How do we know those boundaries really hold?
AI agents are moving beyond generating answers toward taking action. They access data, call tools and trigger workflows, often through APIs and increasingly through protocols such as MCP.
Risks include tool misuse, identity and privilege abuse, goal hijacking and unsafe delegation.
- Who is acting? What are they allowed to call?
- On which data, under which delegated authority and in which business context?
- How is that decision enforced? How do we test that the assumption is actually true?
Governance guides each step
- DefineDefine permitted APIs, MCP tools and actions.
- EnforceEnforce identity, authorization and least privilege.
- ObserveObserve invocations and preserve evidence.
- ValidateValidate downstream API authorization.
- ImproveRetest critical security assumptions.
We’ll discuss how to put these steps into practice, including tests of dangerous combinations of otherwise legitimate capabilities and permissions.
Venedy
Actively testing the downstream APIs and business logic across identities to identify authorization flaws and produce reproducible evidence that intended boundaries hold or demonstrate where they fail.
What we’ll discuss
Putting governance into practice and testing the results
A token may be valid. The agent may have the expected scope. The gateway may route the request correctly. Yet an underlying API can still expose another customer’s object, allow an unauthorized function or violate a business rule.
A permitted tool call does not automatically mean the underlying business action is authorized. Active security testing helps uncover these gaps.
- AI Governance: How to shape responsibilities and rules for AI agents.
- API & MCP Security: How agents interact securely with APIs and tools.
- Authorization & Agent Identity: Who can act and what they can access.
- Security Validation: How to test security boundaries.
- AI Agent Risks: What risks can arise when using AI agents.
- Continuous Assurance: How to maintain security as systems change.
A concrete security chain
User → Agent → MCP / API Gateway → Tool → Backend API → Business Action
At every boundary: who is acting? What are they allowed to call? On which data, under which delegated authority and in which business context? How is that decision enforced, and how do we test that the assumption is actually true?
The morning
A practical conversation
A focused morning for security, platform, engineering and technology leaders considering how to bring agentic AI into production without losing control over what those agents can actually do.
Planned agenda at WERK1. Presentation details are still to be confirmed.
Arrival & breakfast
Coffee, Bretzels and conversation to start the day.
Session 1: AI Governance in Action
Details will follow.
Session 2: AI Governance in Practice
Details will follow.
Closing
A brief wrap-up to close the morning.
Take a seatJoin us
Join us
for breakfast.
Coffee, Bretzels and a discussion about securing AI agents and the APIs they use. Request your place and we’ll email you with the next steps.
2 October 2026 · 09:00 - 11:00
WERK1, Munich
Questions about the event?
event@venedy.io
Thank you
Your request has been received.
We have just sent you an email. Open the confirmation link in it and confirm your request on the page, or it will not reach us. Please also check your spam folder. We then review your request and get back to you by email. Your place is reserved only once we have confirmed it.
You can also request a place by email: event@venedy.io