TL;DR: MCP server security is a control problem as much as a software problem, with Jozu saying these servers sit inside privileged agent workflows. Governance has to cover the execution path, or registry checks alone will not limit data theft, unsafe actions or code execution.
Editorial analysis by NHI Mgmt Group, based on content published by Jozu: “MCP Server Security: Risks, Best Practices, and Enterprise Controls”.
Key questions
Q: Why do MCP servers create a bigger secrets risk than ordinary package installs?
A: Because the threat is not only code on disk, but code that executes inside a real user context and can read live credentials immediately.
Q: How do security teams know whether MCP server governance is working?
A: They should be able to answer four questions at any time: what servers exist, which are official, what credentials they can use, and what systems they contact.
Q: What breaks when MCP servers are trusted without registry and admission controls?
A: A trusted MCP server can become a hidden execution path for data theft, unsafe actions or code execution.
Practitioner guidance
- Inventory all MCP servers in use Sweep developer laptops, IDEs, agent runtimes, CI/CD systems and production clusters to identify unmanaged servers and unknown dependencies.
- Centralise approved servers in an internal registry Mirror approved MCP servers into a private registry and make it the only source agents and IDEs can pull from.
- Require signed admission policy for every artifact Block any MCP server that lacks verified signature, provenance and scan results before it can load.
Bottom line: MCP server security is a control problem as much as a software problem, because these servers sit inside privileged agent workflows.
Glossary terms: MCP — Model Context Protocol, Artifact Admission Control, Tool-level Authorization, Tamper-Evident Audit Log
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Registry trust must be separated from build trust: The central governance mistake in MCP security is assuming that a signed artifact is automatically a safe artifact. The article's Mini Shai-Hulud example shows why that premise fails when an attacker owns the build pipeline or the release workflow. The implication is that admission logic has to sit outside the pipeline's trust boundary, because provenance inside the pipeline is not the same thing as trust in the environment that consumes it.
A few things that frame the scale:
- 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.
- Organisations that describe themselves as confident in their AI deployment actually experience a 72% security incident rate, compared to 33% for those who remain cautious, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: Who should own MCP server risk in an IAM programme?
A: Ownership should sit across IAM, platform security, and the team operating the server, with clear accountability for credential scope, access review, and revocation. If the server can touch production tools, it should be governed like privileged machine identity infrastructure rather than a developer convenience layer.
👉 Read our full editorial: MCP server security now needs registry, runtime and audit controls