Skip to content
jagmarques/asqav-mcp
MCP Security & Auth
A Model Context Protocol server that enforces policy checks, gates AI actions, and creates verifiable audit trails for autonomous agents
Python
·
Latest v0.3.7 · 4d ago
Security brief →
Features
-
Enforce tool policies with three‑tier enforcement (strong, bounded, detectable)
-
Gate actions before execution and produce signed approval/denial decisions
-
Check policies in real time to allow or block AI requests
-
Sign actions into a tamper‑evident audit trail (ML‑DSA / FIPS 204 compatible)
-
Verify and list past audit records for any agent
No immediate action
v0.3.7
New feature
·
Session state digest in receipts
Review required
v0.3.6
New feature
·
Auth
Crypto / TLS
MCP proxy + binding check
No immediate action
v0.2.0
New feature
·
Enforcement tools + MCP registry assets
No immediate action
v0.3.2
New feature
·
MCP scanner + smithery.yaml
No immediate action
v0.3.3
Feature
·
verify_output + preflight_check
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
About
Languages
Python
·
Dockerfile
Search tools, categories, lists, and users
Use ↑↓ to navigate, Enter to open, Esc to close
No results for ""
⌘K to open
↑↓ navigate
⏎ open
