Skip to main content
Free alpha · passive local diagnostic

See what your agents can reach.

Before you add another guardrail, inventory the authority already sitting beside your agents. EMILIA Scan reports configured reach and its own blind spots. It does not launch a server, test a credential, or call home.

npx @emilia-protocol/scan authority
01

Configured reach

Inventories supported agent configuration, declared MCP servers, credential-shaped fields, ambient credential files, and permission rules.

02

Private local pass

Parses bounded files in memory. It launches no configured server and makes no network request. Report files are created owner-only.

03

Blind spots included

Names unsupported formats, malformed sources, invisible runtime tools, and operation surfaces it could not classify instead of declaring them safe.

Honest by default

No reassuring green check from an incomplete scan.

1
Signals found
Review the reachable authority and configuration conditions named in the report.
2
Malformed input
At least one supported configuration source could not be trusted as parsed.
3
Surface not visible
The config-only scan could not see or classify the operation surface. This is not a clean bill of health.

Exit code 0 is intentionally unavailable in configuration-only mode because the scanner does not launch servers and therefore cannot establish complete operation coverage.

Inventory first. Classify second. Enforce separately.

The scanner tells you where to look. It does not claim the action is authorized.

Give the same package an MCP tool list or OpenAPI document to propose which visible operations may need action-bound evidence. Review that proposal yourself. Nothing is enforced until a guard completely mediates the real executor path under your pinned policy and keys.

npx @emilia-protocol/scan ./tools.json
npx @emilia-protocol/scan ./openapi.json
Free AI Agent Authority Scanner — EMILIA | EMILIA