This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+7 more
ReleasePort's take
Light signalPyPI classifier for the package has been updated from Beta to Production/Stable status, improving discoverability. Several documentation enhancements were added, including new MCP transport proxy details and architecture principles.
Why it matters: Patch deployments now surface as stable; update dependent tooling to reference the Production/Stable classifier. Review the updated README and MCP_PROXY_DESIGN_PRINCIPLES.md before next release planning.
Summary
AI summaryMinor fixes and improvements.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
MCP transport proxy adapter surfaced in main README integrations table. MCP transport proxy adapter surfaced in main README integrations table. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Feature | Medium |
MCP proxy added to README_PYPI.md features list with quick-start commands. MCP proxy added to README_PYPI.md features list with quick-start commands. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Feature | Medium |
Authorization capability tokens explained using academic framework references. Authorization capability tokens explained using academic framework references. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Feature | Medium |
Copy updated acknowledging HRU undecidability of access-control safety. Copy updated acknowledging HRU undecidability of access-control safety. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Feature | Medium |
MCP transport proxy 'what's new' callout added to README hero section. MCP transport proxy 'what's new' callout added to README hero section. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Feature | Medium |
New MCP_PROXY_DESIGN_PRINCIPLES.md document mapping architecture to Saltzer-Schroeder principles. New MCP_PROXY_DESIGN_PRINCIPLES.md document mapping architecture to Saltzer-Schroeder principles. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Refactor | Medium |
Repository URLs updated from avp-sdk to agentveil-sdk for brand consistency. Repository URLs updated from avp-sdk to agentveil-sdk for brand consistency. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Refactor | Medium |
PyPI classifier updated from Beta to Production/Stable status. PyPI classifier updated from Beta to Production/Stable status. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Refactor | Medium |
mcp-proxy keyword added to pyproject.toml for PyPI search visibility. mcp-proxy keyword added to pyproject.toml for PyPI search visibility. Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Refactor | Low |
Repository URLs changed from 'avp-sdk' to 'agentveil-sdk' across metadata and docs. Repository URLs changed from 'avp-sdk' to 'agentveil-sdk' across metadata and docs. Source: granite4.1:30b@2026-05-23-audit Confidence: low |
— |
Full changelog
[0.7.15] - 2026-05-12
Post-launch polish release: discoverability fixes for the v0.1 MCP Proxy
adapter and Tier 1 differentiator framing per the AgentVeil design principles
roadmap. Zero production code changes; documentation, metadata, and design
narrative only.
Changed
- Bumped PyPI
Development Statusclassifier from4 - Betato
5 - Production/Stableto match the project's commercial-bar discipline. - Surfaced the
agentveil-mcp-proxyMCP transport proxy adapter in the
top-levelREADME.mdintegrations table alongside framework adapters,
Bedrock, and Microsoft AgentMesh. - Surfaced the MCP transport proxy in
README_PYPI.mdfeatures list and
added a dedicated section with quick-start commands and a link to the
subproject README. - Added
mcp-proxykeyword topyproject.tomlfor PyPI search discovery. - Reframed customer-facing authorization narrative as capability tokens
(signed, scoped, time-bounded, replay-resistant, attenuatable) per Mark
Miller (2006) and Macaroons (NDSS 2014) discipline. AVP's existing
similar_5mscope expansion already implements these properties; this
release names them explicitly. - Adjusted customer copy to acknowledge HRU 1976 undecidability of the general
access-control safety problem. AVP claims constrained, auditable, reversible
decisions within the practically decidable policy subset, not unconditional
safety. - Updated public repository URL references in
README.md,README_PYPI.md,
pyproject.toml,AGENTS.md, andagentveil_mcp/server.py, and refreshed
customer-facing example paths inagentveil_mcp/README.md,
examples/proof_pack/README.md, andmcp_server/README.mdfromavp-sdk
toagentveil-sdkafter the GitHub repository rename for brand consistency
with theagentveilPyPI package name. Operator-local
/Users/.../avp-sdk-publicrelease-smoke paths remain unchanged. - Added an MCP transport proxy "what's new" callout to the top-level
README.mdhero section surfacing the v0.7.15 ship and IDE client coverage
without disrupting the AVP product-led hero tagline.
Added
- New design principles document at
docs/MCP_PROXY_DESIGN_PRINCIPLES.md
mapping AgentVeil MCP Proxy architecture to the eight Saltzer-Schroeder
(1975) principles: economy of mechanism, fail-safe defaults, complete
mediation, open design, separation of privilege, least privilege, least
common mechanism, and psychological acceptability.
Audit References
- Discoverability fixes: PL-1, PL-2, PL-3, PL-4, caught reviewer-side after
the P11.5 ceremony. - Differentiator items: #1 Saltzer-Schroeder citation, #2 HRU honest framing,
#3 capability discipline reframing - Tier 1 free items from
avp_mcp_proxy_differentiators_roadmap.md.
Validation
- No production code changes. Pytest baseline unchanged: 642 passed, 1 skipped.
- Bandit static analysis unchanged: 6 LOW, 0 MEDIUM, 0 HIGH.
- All refined customer-facing wording scans (AI-attribution, prohibited
product terminology, production-grade strict reading) return zero matches
post-edit.
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
About creatorrmode-lead/avp-sdk
Trust, identity (W3C DID), and EigenTrust reputation for AI agents. Attestations, disputes, sybil detection, IPFS audit anchoring.
Related context
Related tools
Beta — feedback welcome: [email protected]