atlassian-mcp

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides instructional content and code templates for building Atlassian integrations, following standard development practices.
  • [EXTERNAL_DOWNLOADS]: References to external packages and MCP servers (such as @anthropic/mcp-atlassian and mcp-atlassian) are for well-known and official implementations used for establishing the MCP connection.
  • [COMMAND_EXECUTION]: The provided configuration examples for Claude Desktop utilize standard commands like npx and uvx to run MCP servers.
  • [SAFE]: Authentication guidance correctly emphasizes using environment variables and professional secrets management (e.g., AWS Secrets Manager, GCP Secret Manager, HashiCorp Vault), and provides explicit warnings against hardcoding credentials in source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 04:38 PM
Security Audit — agent-trust-hub — atlassian-mcp