# Decision State MCP

> Use this tool when you need to store and retrieve decision-relevant state outside of a chat context, enabling easy access to goals, constraints, facts, and decisions for AI models like Claude Code or Codex. It solves problems of contextual data loss and improves decision-making by providing a compact and accessible state storage. Ideal for use cases where chat context is limited, and external state management is necessary.

Canonical page: https://skillsregistry.net/skills/koolercat-mcp-state  
JSON: https://api.skillsregistry.net/v1/skills/koolercat-mcp-state

## Description

A small MCP server that stores and retrieves compact decision-relevant state (goals, constraints, facts, decisions) outside the chat context, enabling easy retrieval for Claude Code or Codex.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x00mgyls8w)
- **Repository:** <https://github.com/Koolercat/mcp-state>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "koolercat-mcp-state"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/koolercat-mcp-state` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/koolercat-mcp-state/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt