iDenfy has launched a Model Context Protocol connector that links Claude and Claude Code to its identity-verification, business-verification and anti-money-laundering services. The company says the connector uses dedicated endpoints designed not to expose personal data such as names, document numbers or document photographs. AML results return statuses and flag types rather than the names of matched people.

Access is controlled through a separate token and granular View or Edit permissions for each product area. iDenfy says permissions are checked on every request, connections can be removed by an administrator and an unused connection expires after seven days. The connector is available to existing customers without an additional fee, with support for other major AI tools planned. These are vendor descriptions and should be verified against the organisation's configuration, data flows and contractual controls before deployment.

The design is useful because it treats an AI assistant as a constrained interface to compliance operations rather than as a general-purpose reader of customer records. Even so, privacy-limited responses do not remove governance obligations. Firms still need to log who authorised a query, distinguish read access from workflow changes, validate how the model interprets status codes and prevent prompts from becoming an unreviewed route into regulated decisions. MCP can simplify integration; it does not transfer accountability away from the firm.

Execution Level Governance- What audit-ready agent governance actually looks like
David Girvin, founder and CEO of Assury argues that model-in-the-loop review, AI governing AI, is fundamentally unreliable for regulated environments: even the best-performing models miss a meaningful share of violations, the reviewing model is typically provided by the same vendor being reviewed, and prompt injection or context poisoning can compromise both the acting agent and its supposed overseer simultaneously. He makes the case for deterministic, architecturally enforced controls instead, walking through Assury's approach of autonomy zones, session risk accumulation, and credential starvation, which lets a compromised agent be cut off from its tools instantly rather than relying on time-boxed access. The conversation touches on why David is sceptical of just-in-time credentialing as a solution for agent security more broadly, since agent sessions don't run on predictable human timescales, along with the current gap between how identity and security vendors are pitching agent protection and what he sees happening at the execution layer in practice. He also discusses the compliance and audit implications of probabilistic decision-making, arguing that regulated industries will increasingly need tamper-evident, hash-chained audit trails that can withstand scrutiny from auditors and regulators who are only beginning to understand agentic risk, and reflects on a named frontier lab's own published framework as an example of the gap between research and practitioner reality. Elsewhere, David reflects candidly on building a bootstrapped security company in an increasingly crowded market, why he turned down aggressive VC funding to stay in control of the product, and what a credible third-party assessment of his own gateway would need to look like given that Assury sits directly in the execution path for every customer's agents.
BrightTALK
Share this post
The link has been copied!