io.github.CSOAI-ORG/ai-bom-mcp

The material explicitly states that no keys or environment variables are required, and no API tokens, cloud credentials, or other sensitive secrets are indicated; therefore credential leakage and abuse exposure appears low.

No remote host endpoints are declared, and the available material does not show a need to send user data to external services; based on the known facts, there is no explicit network egress path.

The system checks indicate executes-code capability, meaning the tool can execute code or processes locally; this is a standard but sensitive MCP capability and should be run in an isolated environment with restricted system access.

As an AI-BOM generation and auditing tool, it would reasonably need to read local project or bill-of-materials-related data and may also write output files; there is no evidence of excessive access in the material, but the exact read/write scope is not documented in the README and should be constrained by least privilege.

Positive signals include an official registry source, an auditable open-source repository, and updates within the last year; these all reduce supply-chain risk. Points to watch are the missing README, undeclared license, and very low community adoption (0 stars), which reduce transparency and external validation, so the source and dependencies should be reviewed before deployment.