mongodb-mcp-setup

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands (env, grep, docker info, echo $SHELL) for environment discovery and configuration verification. These operations are diagnostic in nature and implemented safely.
  • [SAFE]: Credential handling is performed securely. The skill explicitly avoids requesting or processing user secrets directly. Instead, it provides instructions for users to store credentials in a local environment file (~/.mcp-env) with restricted filesystem permissions (chmod 600).
  • [SAFE]: Sensitive information exposure is mitigated in diagnostic outputs. The skill uses sed to mask environment variable values (e.g., MDB_MCP_CONNECTION_STRING) before displaying them to the user.
  • [SAFE]: The skill provides proactive security guidance, such as warning users against the risks of using permissive IP access lists (0.0.0.0/0) for Atlas Service Accounts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 03:48 PM