book-recommender

The materials explicitly state that no keys or environment variables are required, and there is no indication that account credentials, API tokens, or other sensitive authentication secrets are needed, so credential exposure appears limited.

No remote endpoints are declared, and the described functionality is limited to searching and filtering a Goodreads dataset; based on the available materials, there is no clear data egress path, though the missing README means runtime network behavior cannot be fully verified.

The objective checks mark this tool as executes-code, meaning it runs locally as a service and has normal code execution capability. This is inherent to MCP tools, and the provided materials do not show it requesting abnormal system privileges beyond its stated purpose.

Functionally, it likely needs access to a locally available dataset or program resources to perform book search/filtering, which may involve reading local files. The description does not indicate writing user files or accessing unrelated data, but the sparse documentation leaves the exact access scope not fully transparent.

A positive factor is that the source code is publicly available for review; however, it comes from a third-party registry, has zero stars, no declared license, unknown maintenance status, and no README, which weakens trust and long-term maintenance signals. This creates some supply-chain uncertainty, though there are no concrete red flags strong enough to classify it as high risk.