Claude MarketplacesSubmit
echology-io avatar

Decompose

echology-io/decompose

Exposes two MCP tools for text classification without an LLM: decompose_text and decompose_url. Every semantic unit gets tagged with authority level (mandatory, prohibitive, directive), risk tier (safety_critical, compliance, financial), and attention score (0 to 10). Built on regex and heuristics, so it runs deterministic and offline in under 500ms for long documents. The filter_for_llm function drops boilerplate and keeps only high-value units, typically cutting 60 to 80 percent of tokens before they hit your context window. Pulled from Echology's AECai platform where it classifies construction specs and contracts, but works across domains. Use it to route high-risk content to specialized chains or pre-filter documents before embedding.

GitHub stars
9
tools
2
transport
STDIO
last updated
Feb 15, 2026
View on GitHub

Tools

2 tools

Public tool metadata for what this MCP can expose to an agent.

decompose_textdecompose any text

decompose any text

No parameter schema in public metadata yet.

decompose_urlfetch a URL and decompose its content

fetch a URL and decompose its content

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

Decompose

CI PyPI Python

Stop prompting. Start decomposing.

Deterministic text classification for AI agents. Decompose turns any text into classified, structured semantic units — instantly. No LLM. No setup. One function call.

Before: your agent reads this

The contractor shall provide all materials per ASTM C150-20. Maximum load
shall not exceed 500 psf per ASCE 7-22. Notice to proceed within 14 calendar
days of contract execution. Retainage of 10% applies to all payments.
For general background, the project is located in Denver, CO...

After: your agent reads this

View the full README on GitHub

Details

Repository
github.com/echology-io/decompose
Category
AI & LLM Tools
Package
decompose-mcp
Transport
STDIO
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1nnar1o avatarkgnnar1o/kgLocal knowledge graph memory MCP server for AI assistants.0stars
2iris-eval avatarIrisiris-eval/mcp-serverStop shipping agents on vibes. Score every agent output for quality, safety, and cost.0stars
3refined-element avatarLightning Enable MCP Serverrefined-element/lightning-enable-mcpAI agent Lightning payments: L402, invoices, wallets, API discovery, budgets, self-serve signup.9stars
4scrypster avatarMementoscrypster/mementoPersistent memory for AI tools. Local-first knowledge graph with hybrid search.9stars
5umitkavala avatarMindpmumitkavala/mindpmProject memory and a control plane for AI coding agents.9stars
6alex-feel avatarMcp Context Serveralex-feel/mcp-context-serverAn MCP server that provides persistent multimodal context storage for LLM agents.8stars