Orca Security MCP

What do you like best about the product?

There was a recurring problem with shadow data: production data getting copied into staging and dev accounts that were nowhere near as locked down, plus data stores nobody even remembered creating. Orca discovers sensitive data across managed, unmanaged, and shadow stores, including files on VMs, containers, and buckets, and then classifies it against categories like PII and payment data. Seeing a forgotten production snapshot sitting in a loosely controlled dev account, and having that tied to how exposed the account was, makes it obvious which copies are genuinely risky versus intentional.

What do you dislike about the product?

A bit of tuning was needed to distinguish sanctioned data copies from the risky ones, since some of the lower-environment data was there on purpose. That said, the configuration was quick to align with our internal workflows.

What problems is the product solving and how is that benefiting you?

It provides real visibility into sensitive data sprawl, including shadow data and misplaced data, so the gap between well-secured production and looser accounts stops being an invisible exposure. It also highlights where AI agents could run into sensitive data they should never be able to touch, turning those risky paths into concrete cleanup work.

What do you like best about the product?

A lot of attention goes to containers these days, but there are still plenty of VMs and long-lived hosts, and those were exactly where our old scanning was the patchiest. Orca covers them in the same model as everything else, showing which host vulnerabilities sit on internet-facing machines, which are tied to privileged identities, and which are genuinely reachable versus buried behind existing controls. That added context lets us prioritize host patching based on real exposure instead of relying on raw CVSS scores.

What do you dislike about the product?

A couple of the older hosts had the usual configurations that warranted a closer look, but the underlying findings were sound, and the added context made them straightforward to interpret.

What problems is the product solving and how is that benefiting you?

It closed the gap between our modern container coverage and our older VM estate. As a result, host risk is no longer prioritized on severity scores alone, but on how exposed it actually is. It also helps us understand when host and VM risk could affect the infrastructure supporting AI agents, or the systems those agents depend on.

What do you like best about the product?

Our business moves fast. Developers, analysts, and PMs are constantly shipping, and AI agents are woven into many of those workflows. We needed visibility that could keep up with that pace—not a slow rollout that would still be incomplete by the time the next agent went live.

Orcca connected to our cloud account, and within days it gave us a real risk picture, including the AI agents: the identities they run as, the endpoints they expose, and the data they could touch. We didn’t have to chase teams to get a clear understanding of our agent services.

What do you dislike about the product?

The main follow-on work was organizing the findings to match how our teams and business units are structured, including grouping agents by owner and function. That organizational step has made ongoing reviews much clearer for leadership.

What problems is the product solving and how is that benefiting you?

This removed the usual deployment barrier and gave us AI agent visibility before we could normally even finish planning the rollout. That speed matters even more as agents and their workflows appear across the state, because they become visible and governable as quickly as teams create them.

What do you like best about the product?

The thing that really changed how we work is the attack path view. Instead of a list of separate findings, Orca shows the full chain: an exposed asset, the vulnerability on it, the identity it can assume, and the sensitive data at the end of that path. Seeing the entire route makes it obvious which single fix can break the whole chain, so we stopped trying to patch everything and started cutting the links that actually matter.

What do you dislike about the product?

In a large environment, the attack path graphs can hold a lot of detail, so we found it most effective to scope to the crown jewel assets first. Once we did that, the overall picture became clear and genuinely useful.

What problems is the product solving and how is that benefiting you?

It moved us from simply counting vulnerabilities to reasoning about exploitable routes, which is a much better use of a small team’s time. It’s especially valuable when AI agents sit somewhere along that route, because we can see how the agents access identities and how the data paths factor into the real chain an attacker could follow. As a result, we fix fewer things, but we reduce the more real risk.

What do you like best about the product?

Orca flagged malicious files and suspicious workflows across our workloads that none of our other tooling had caught, including scenarios where an abused AI agent could have been used to plant or trigger malware. It goes beyond simple hash matching, picking up things like cryptominers and web shells that agents might deploy or invoke as part of a compromised toolchain. Because scanning happens off the workload at the storage and configuration layer, there’s nothing for the malware to hide from on the box itself, and it also covers hosts and agent-linked paths we never would have pointed a dedicated scanner at.

What do you dislike about the product?

We aligned the Orca agent-aware malware and threat findings with our existing endpoint response processes, which helped us fold that context smoothly into the way the team already operates.

What problems is the product solving and how is that benefiting you?

It gave us malware and abuse visibility across our cloud workloads and the agent paths that were previously blind spots. We can see not just that malware exists, but how AI agents could be used to deploy or spread it, and then cut those routes off.

What do you like best about the product?

We had a vague sense that credentials and secrets were scattered across our environment, but we didn’t have a clear map of which ones agents could actually see. Orca surfaced hardcoded API keys, SSH private keys, and database credentials in places agents or their tools might read—config files, storage buckets, and logs. It doesn’t just pattern-match; it uses entropy and the surrounding context to decide whether a string is truly a secret, which keeps the noise down. Seeing each secret in the context of agent reachability made it clear which exposures could be triggered by agents and needed immediate cleanup.

What do you dislike about the product?

We spent some time defining suppression rules for the test credentials in our sandboxes, so that agent-relevant secrets stayed front and center in the findings.

What problems is the product solving and how is that benefiting you?

It turned secret sprawl from an abstract worry into a concrete, prioritized cleanup list, with a special focus on the secrets that AI agents could stumble over. Exposed credentials have become a tracked, agent-aware risk rather than something we had to get to eventually.

What do you like best about the product?

Having Orca scan our infrastructure as code and our pipelines has been a genuine shift-left win for the AI agents. We started catching templates and configuration snippets that would have granted agents broad, long-lived permissions or exposed new agent endpoints before any of those changes ever deployed. Because Orca ties these IaC findings back to the same risk model it uses for the running environment, we can clearly see that a misconfiguration flagged in code is the same kind of agent exposure we’d otherwise be chasing down in production later.

What do you dislike about the product?

We worked closely with our platform team to integrate agent-focused checks cleanly into our build steps, and to decide which misconfigurations should trigger a warning versus block a deployment.

What problems is the product solving and how is that benefiting you?

It shifts cloud and agent security left in a way that actually sticks. We’re catching reachable, exploitable agent misconfigurations during code review instead of after agents are already live and exposed, which has made the whole pipeline safer without adding friction.

What do you like best about the product?

Orca gave us a much clearer picture of where sensitive data actually lives in relation to our AI agents. It surfaced PII in storage, secrets in places agents might read, and old database snapshots sitting in accounts that newly created agents were able to reach. The real value is the context: each finding shows what the data is, whether it’s exposed, and which agents and identities can access it. That turned what could have been an overwhelming inventory into a clear, prioritized list of data our agents should never be able to touch, along with the paths we needed to close.

What do you dislike about the product?

We spent a bit of time upfront tuning the data classification and agent reachability settings to align with our own definitions of sensitive information, as well as the agent access paths we consider unacceptable.

What problems is the product solving and how is that benefiting you?

It folds data security into the same agent-aware risk picture as misconfigurations and identities, so “where is our sensitive data, and which agents can reach it?” is finally a question we can answer continuously.

What do you like best about the product?

Our finance and enterprise risk teams wanted to understand AI agent risk in business terms, not just issue counts or an abstract idea of "agent exposure." Orca’s context—what data an agent can touch, whether it can reach internet-facing services, and which identities and systems sit behind its paths—lets us group agent-driven risks around business-critical assets and regulated workflows. It’s not a full quantitative risk engine, but it has given us a structured way to discuss which agent behaviors matter most to revenue, compliance, and our contractual obligations.

What do you dislike about the product?

We still add some business mapping on our side for certain agent-centric technical risks, so they line up neatly with the revenue streams and the contractual exposure.

What problems is the product solving and how is that benefiting you?

It has moved our security discussions with Finance and Enterprise Risk from “here is a pile of agent findings” to “here are the top agent-driven threats to the system” that actually drive cost and compliance exposure.

What do you like best about the product?

Our product team constantly runs experiments, turning features on and off with flags that are increasingly evaluated or executed by AI agents. Orca doesn’t try to live in the feature-flag layer; instead, it watches the underlying cloud identity and the agent posture. When an experiment gives an agent broader access than intended, or opens up a test path to sensitive data, Orca picks it up on its next assessment of the cloud and agent surface and flags it. Developers don’t have to change how they ship experiments, but security can still see where agent-driven flags might create unexpected exposure.

What do you dislike about the product?

Explaining to some product folks why the temporary agent-powered experiments still need proper access controls took a few rounds of education, even with the Orcas findings on hand.

What problems is the product solving and how is that benefiting you?

It keeps up with experimentation-heavy, agent-driven development without slowing it down. Orca watches the surfaces where risk actually materializes—when agents toggle, evaluate, or act on feature flags.