Jinero

The materials state that no keys or environment variables are required, and no API tokens, account credentials, or other highly sensitive secrets are mentioned, so credential exposure risk appears low.

System checks show that it connects to the remote endpoint jinero.online; as a design-oriented MCP, user inputs or generated content may be sent to that service for processing. The endpoint is generally related to the stated function, but the materials do not specify what data is transmitted, how it is stored, or the privacy boundaries.

The system flags it as executes-code, indicating the tool can start local processes or execute code. This is a normal high-privilege capability for MCP tools by itself; the materials do not show clearly excessive system permissions beyond the design use case, but it should still be run in a constrained environment.

The available materials do not state that it reads or writes local files, accesses databases, or handles data beyond normal design inputs and outputs, nor do they show requests for broad disk or system resource permissions. Documentation is sparse, so the exact data-access boundary is unclear, but there is no explicit evidence of overbroad access.

Its presence in the official Registry and updates within the last year are meaningful risk-reducing signals; however, there is no open-source repository, no declared license, and no README, which prevents auditing the implementation and dependencies, while community adoption lacks strong verifiable signals. Supply-chain transparency is therefore limited, and it should be managed like a closed-source third-party component.