Decompose MCP Server

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

Local serverstdioPython

What is the Decompose MCP server?

Deterministic text classification for AI agents. Decompose turns any text into classified, structured semantic units — instantly. No LLM. No setup. One function call. The decompose mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

  • Fast — <500ms for a 50-page spec
  • Deterministic — Same input always produces same output
  • Offline — Works air-gapped, on a plane, on CI
  • Composable — Your agent's LLM reasons over the structured output — decompose handles the preprocessing

Its toolset

Everything the assistant can do here goes through one of these:

  • Fast — <500ms for a 50-page spec
  • Deterministic — Same input always produces same output
  • Offline — Works air-gapped, on a plane, on CI
  • Composable — Your agent's LLM reasons over the structured output — decompose handles the preprocessing
  • Field — Values
  • authority — mandatory, prohibitive, directive, permissive, conditional, informational
  • risk — safety_critical, security, compliance, financial, contractual, advisory, informational
  • type — requirement, definition, reference, constraint, narrative, data
  • irreducible — true/false
  • attention — 0.0 - 10.0
  • entities — standards, codes, regulations
  • actionable — true/false

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at decompose-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Decompose's toolset — Fast, Deterministic, Offline and 11 more — is a fair guide to whether it matches your workflow. It is maintained by echology-io; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Decompose.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the decompose mcp server does with a few real requests.

Available tools

ToolWhat it does
Fast<500ms for a 50-page spec
DeterministicSame input always produces same output
OfflineWorks air-gapped, on a plane, on CI
ComposableYour agent's LLM reasons over the structured output — decompose handles the preprocessing
FieldValues
authoritymandatory, prohibitive, directive, permissive, conditional, informational
risksafety_critical, security, compliance, financial, contractual, advisory, informational
typerequirement, definition, reference, constraint, narrative, data
irreducibletrue/false
attention0.0 - 10.0
entitiesstandards, codes, regulations
actionabletrue/false
OpenClawThe OpenClaw tool exposed by this server.
BlogThe Blog tool exposed by this server.

How to install the Decompose MCP server

{
  "mcpServers": {
    "decompose": {
      "command": "uvx",
      "args": ["decompose-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Decompose to Fast.
  • Use Decompose to Deterministic.
  • Use Decompose to Offline.

Frequently asked questions

It connects Decompose to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Fast, Deterministic, Offline, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Decompose directly.