GuardianShield is an MCP server for scanning code, files, directories, diffs, and model inputs/outputs for vulnerabilities, secrets, prompt injection, and PII. It also checks dependencies against CVEs, supports safety profiles, false-positive tracking, audit logging, and SARIF export for CI.
From the registry: AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
$ pip install guardianshieldhttps://pypi.org/project/guardianshield/Please install the `guardianshield` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install guardianshield** — Install via pip Run: `pip install guardianshield` (https://pypi.org/project/guardianshield/)
Canonical MCP server config (stdio transport):
- command: `guardianshield-mcp`
- args: []
- optional environment variables:
- `GUARDIANSHIELD_PROFILE`: Default safety profile (example: `general`)
- `GUARDIANSHIELD_AUDIT_PATH`: Path to SQLite audit database (example: `~/.guardianshield/audit.db`)
- `GUARDIANSHIELD_DEBUG`: Enable debug logging (example: `1`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GUARDIANSHIELD_PROFILEDefault safety profileGUARDIANSHIELD_AUDIT_PATHPath to the SQLite audit databaseGUARDIANSHIELD_DEBUGEnable debug loggingDead code, security, secrets detection and code quality for Python, TypeScript, Go.