This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+2 more
Summary
AI summaryUpdates Performance, Links, and https://pypi.org/project/decompose-mcp/ across a mixed release.
Full changelog
Decompose v0.1.0
The missing cognitive primitive for AI agents. Decompose any text into classified, structured semantic units — instantly. No LLM. No setup. One function call.
Features
- Authority classification — mandatory, prohibitive, directive, permissive, conditional, informational (RFC 2119)
- Risk scoring — safety_critical, security, compliance, financial, contractual, advisory, informational
- Attention scoring — 0.0-10.0 priority score (authority weight × risk multiplier)
- Entity extraction — ASTM, ASCE, IBC, OSHA, ACI, AISC, AWS, ISO, EN standards and codes
- Irreducibility detection — flags content that must be preserved verbatim
- Financial extraction — dollar amounts, percentages, retainage, liquidated damages
- Date extraction — deadlines, milestones, notice periods
- MCP server —
decompose_textanddecompose_urltools for any MCP-compatible agent - CLI — pipe text or pass inline, pretty or compact output
- SSRF protection — URL validation with IP blocklist for
decompose_url
Performance
- ~14ms average per document on Apple Silicon
- 1,000+ chars/ms throughput
- Zero API calls, zero cost, works offline
- Deterministic — same input always produces same output
Install
pip install decompose-mcp
Links
- PyPI
- Documentation
- Blog: When Regex Beats an LLM
- ClawHub Skill — search
decompose-mcp
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 echology-io/decompose
Decompose text into classified semantic units with authority, risk, attention scores, and entity extraction. No LLM. Deterministic. Works as MCP server or CLI.
Related context
Related tools
Beta — feedback welcome: [email protected]