This release adds 5 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Summary
AI summaryAdded multiple new features including confident_spread, YAML_ALLOWED_KEYS whitelist, plain-text formula output, HTML stripping, and deduplication by sign.
Full changelog
v2.3.0
New Features
- confident_spread: normalized spread for sign classification, replaces raw cosine threshold
- YAML_ALLOWED_KEYS whitelist: prevents internal server fields from leaking into user files
- plain-text formula: format_entity_compact returns clean text without HTML
- strip_formula_html: removes formula HTML blocks before embedding
- dedup_by_sign: compact formula deduplicates children/parents by sign
Fixes
- Updated README with new formula format and tool descriptions
- Fixed server.json repository URL (nouz-mcp → NOUZ-MCP)
- Updated glama.json with keywords and description for Glama registry
Tools
- 13 MCP tools with improved descriptions for TDQS scoring
- All tool descriptions now include side effects, usage guidelines, and sibling differentiation
Full Changelog: https://github.com/KVANTRA-dev/NOUZ-MCP/compare/v2.2.3...v2.3.0
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 KVANTRA-dev/NOUZ-MCP
Semantic knowledge graph for Obsidian. Three modes (pure graph / semantic classification / strict hierarchy)
Related context
Beta — feedback welcome: [email protected]