ai.childadhd/library

The materials explicitly state that no keys or environment variables are required. No API key, OAuth token, or other sensitive credential is mentioned, so credential leakage and abuse risk appears limited.

System checks confirm outbound network access to the remote endpoint childadhd.ai. As a networked MCP tool, user queries may be sent to that service, but the materials do not describe transmission scope, logging, or retention practices, so outbound data handling warrants caution.

System checks indicate that the tool executes code or starts a local process, which is a common MCP behavior. The available materials do not show requests for system privileges beyond its stated purpose, but the exact capabilities are undocumented, so it should be run with least privilege.

There is no README or permission documentation defining what local files, caches, or other resources it may read or write. While there is no explicit evidence of overbroad access, the combination of local code execution and missing documentation makes data access boundaries insufficiently transparent.

Positive factors include distribution via an official registry and maintenance within the last year, both of which reduce supply-chain risk. However, the absence of a public source repository, no declared license, and low community adoption limit code and dependency auditability, so caution is appropriate.