Principal Support Engineer

The four questions Chicago wouldn't let go. * September 23, 2026 * By Laura Heritage Nine seconds. That's how long it took an ungoverned AI agent to find an over-scoped token and wipe a production database. This was how Tyk's Mark Gurvis opened its recent LEAP on Tour event in Chicago. What followed wasn't a polite Q&A. The room split into working sessions, insurance next to consumer goods next to applied AI and banking. Fourteen people from twelve companies, from the C-suite to the teams building it, came at MCP governance from different angles and found they were circling the same problems. Then pressed each other on them. When everyone came back together, Tyk Technologies Ltd worked through what each table had landed on. Four questions had surfaced across every session, so Tyk Technologies Ltd has written them up ready for you to share with your team. 1. How do you actually track both the human's identity and the AI agent's identity on the same call? Imagine two users - let's call them Alice and Bob - both logging in through Keycloak. Alice has read-only access to customer records. Bob's entitlements include refunds. When either of them triggers an agent to act, the original login token, which carries a broad set of entitlements, never gets forwarded downstream. At the gateway, it gets exchanged for a new token scoped to exactly what that one action needs, reducing the blast radius to a single call. Two claims matter here: * sub, the subject, which is the human and stays identical across every hop no matter how many services the request touches. * azp, the authorized party, which is whichever agent or app is currently holding the token and changes at every exchange. aud and scope get reset the same way, narrowed down to one backend and one permitted action each time. So, when Alice's agent tries a refund, it gets rejected; her scope never included it. When Bob's agent tries the same thing, it succeeds, scoped specifically to that single refund call. You always know who asked and what's currently acting on their behalf, at every step. Tyk Technologies Ltd closed the LEAP on Tour Chicago event by putting exactly this scenario on screen and running it live. 2. Is securing MCP actually different from securing any other API? Mostly no. The principles don't change: Authenticate, authorize, scope tightly, log everything. What does change is the blast radius. An agent can chain several tool calls on its own, in sequence, without a human approving each one. So the same API security discipline still applies, it just has to run at every hop instead of once at the front door - because the thing making the second and third call isn't a person checking their own judgment anymore. 3. What happens when multiple teams' agents compete for the same rate-limited tool? This one came up at nearly every table, usually with the assumption that nothing could be done about it yet. But there is a solution, and it ties straight back to the previous question. Rate limiting is ordinary practice on APIs, but here it has to operate one level down, on the primitives themselves (tools, resources, and prompts), rather than on the MCP server as a whole. That is what per-consumer, per-primitive rate limiting and quotas are for. You can cap how much of a shared tool any one team's agents can consume. That means one team's automation can't starve another team's access. What Tyk Technologies Ltd don't decide for you is the policy at the moment a limit is hit. Whether that request queues, fails outright, or escalates to a human is a call your organization makes based on what the tool actually does. Tyk Technologies Ltd is extending the same model to LLM token and cost management too. 4. Could your organization actually produce a full list of every MCP server it touches today? For most in the room, the honest answer was no. A few people pointed out that Claude or Copilot's own admin console already gives them a list, and that's a fair partial answer. It certainly covers what's registered inside that one client. But this list stops there. It won't show you a headless agent calling a server directly with no chat client involved. It won't reconcile across every vendor your teams use. And it's not an audit trail anyone outside that console can check. That's the same blind spot API sprawl led to a few years ago, and it deserves the same fix: One living registry tied to your existing developer portal, naming what each server does and who owns it, that both your people and your agents check before a call is ever made. Where this leaves Tyk Technologies Ltd. As Tyk Technologies Ltd has just shown, all four of these pressing questions already have an answer today. Some of that answer is product-related, while some of it needs people and processes alongside the technology. The question that barely came up in Chicago is the one Tyk Technologies Ltd raised ourselves, and it is where this gets hard. A token is a pass made out to one specific door. The moment one agent hands work to another agent, and that one hands it on again, the pass no longer matches the door in front of it and the service on the other side refuses to open. Identity providers are strict about this by design, Keycloak and Entra among them, and there's no setting that waves it through. That's the next boundary, and it's the conversation Tyk Technologies Ltd most want to have at the rest of its LEAP on Tour events. The sharpest version of all these conversations happens in the room. Its next two stops are New York (nearly at capacity) on October 21 and Dallas on November 4. Book your seat now and bring your hardest questions. Share the Post:

Building the next generation of API experiences for Gen Z. * June 23, 2026 * By Laura Heritage Tyk Technologies Ltd. has all read the big consultancy firms' reports on what Gen Z wants from their banking experiences, but when did you last speak to a member of Gen Z to get input firsthand? Tyk's Laura Heritage tackled this head-on at the LEAP 2026 conference, through a lively panel discussion with Gen Z consumer Sidney Olson and Reuben Piryatinsky, CEO of Altitude Consulting. Gen Z's financial life. Gen Z is the first generation to grow up in a fully digital world. They expect instant, embedded, transparent financial services to be available through seamless and intuitive apps. What does that look like on an individual basis? Sidney outlined her own banking needs as an insight into what's important to Gen Z: * A main bank account, accessible via an app * A local branch for depositing cash (example: depositing tips when working as a server) * The ability to pay for things and receive money with an app (example: using Venmo to pay for Girl Scout cookies and to receive repayments from friends) * Support with saving (example: a bank account that puts the first $x of a paycheck into a savings account, while still leaving enough in the main account for rent, food, and fun) * Financial services shaped intuitively around need (example: Instagram uses an algorithm to know what users want, so why can't banks?) * Support from humans with key banking tasks, such as opening accounts. Would Gen Z trust AI as part of this? Perhaps. Sidney explained that she would be open to recommendations from AI as help with saving and handling money, but would be hesitant to allow AI free reign in implementing those recommendations. The case for Open Banking. Altitude Consulting CEO Reuben explained that Open Finance is the key to delivering the types of experiences that will satisfy Gen Z. At its core, Open Finance is about being able to share your financial data securely and with consent, from your primary institution to other financial institutions and apps. Consumers won't ask for it by name but they're increasingly demanding the services it facilitates. Gen Z (and Gen Y) expect full, always-on banking capabilities that they can use in a self-serve manner. If social media apps can roll out regular updates without taking services offline, banks need to follow suit to earn Gen Z's trust. Achieving the high performance and low latency required support this means focusing on three areas: * APIs: things like response compression on payloads and caching for static reference data. * Event-driven architectures: webhooks for notification and consent events, plus Kafka-based event streams. A lot of the systems banks are using weren't built for these real-time data demands, so need to adapt. * The FDX standard, to ensure all the data needed is available. FDX isn't so much a requirement for regulation as it is a driver of innovation - it's the foundation of the modern Open Banking experiences that Gen Z demands. Spotlight on security. Consent, control, transparency, and security are the cornerstones of Open Finance. Recent agentic AI security incidents have highlighted the importance of the latter, increasing the need to focus on "know your agent" processes, to understand which agents are connecting to financial data, for what purpose, and how they're going to use the data. Data minimization and the principle of least privilege apply. Interestingly, Sidney doesn't dwell on the security risks of banking. Having grown up with tech all around, she trusts her bank to provide secure digital experiences. Such trust is easily broken and difficult to regain, meaning financial institutions need to work hard behind the scenes to deliver it continuously. At the same time, banks must provide the data sharing that Gen Z expects as part of seamless financial experiences. One of the core elements of Open Finance is the ability for the account owner to provide consent for sharing data in a way that gives them transparency and control, so they see which organizations they're sharing data and for what purpose. Users must also be able to revoke consent at any given moment. Financial institutions that have implemented Open Banking capabilities can provide consent dashboards for this, enabling users to see which third parties they've permissioned to access their data to easily revoke it. AI in financial services. Reuben observes that Open Finance has been a major catalyst in terms of data standardization. Financial institutions are standardizing data across their business lines, products and departments, focusing on enhanced data governance and visibility. This is reducing the siloed nature of financial institutions while also making them ready for AI use cases, as AI requires access to high-quality data. Many financial services organizations are already employing AI in internal models, restricted to specific use cases, but there aren't yet many examples of agentic AI connected to financial data. While the infrastructure for it is there, end-to-end security and governance systems need to mature before agentic AI can flourish in the financial world. This is likely to occur over the next few years. At the same time, banks need to remember the human element. Sidney is likely to adopt an app once she sees it take off among her peers. This kind of social proof is key to earning Gen Z's trust when it comes to new products. Banks need to win hearts and minds, not just deliver technical capabilities. Share the Post: