Skip to content

jagmarques/asqav-mcp

v0.3.7 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 4d MCP Security & Auth
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agent ai-agents ai-governance ai-security audit-trail claude
+11 more
claude-code claude-desktop compliance cursor eu-ai-act mcp mcp-server model-context-protocol policy-enforcement python quantum-safe

Summary

AI summary

Receipts now include session state digest with drift detection via root-level flag.

Changes in this release

Feature Medium

Receipts now carry `mcp_session_state` with capability digest pair captured at session start and signing time.

Receipts now carry `mcp_session_state` with capability digest pair captured at session start and signing time.

Source: llm_adapter@2026-05-31

Confidence: high

Feature Low

`state_changed=true` is hoisted to the payload root when session state drifts.

`state_changed=true` is hoisted to the payload root when session state drifts.

Source: granite4.1:30b@2026-05-31-audit

Confidence: low

Full changelog

Transparent proxy verify-state mode (#54): receipts now carry mcp_session_state with a tools/prompts/resources/capability digest pair captured at session start and re-captured at signing time; state_changed=true is hoisted to the payload root on drift, with zero wire-vocabulary change.

Claude Managed Agents integration guide (#50) and a README link to it. Tier-1 server tests (#52) covering the five highest-CRAP enforcement paths. README lead repositioned to a painkiller frame (#56). Comment-hygiene and lint cleanup across src/.

PyPI: https://pypi.org/project/asqav-mcp/0.3.7/

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.

Share this release

Track jagmarques/asqav-mcp

Get notified when new releases ship.

Sign up free

About jagmarques/asqav-mcp

AI agent governance MCP server with policy enforcement, quantum-safe audit trails (ML-DSA), multi-party authorization, and compliance reporting. Check policies, sign actions, and verify signatures through MCP tools.

All releases →

Beta — feedback welcome: [email protected]