# ITHZ MCP

> Use this tool when you need to manage and store project memory for AI agents, enabling efficient context switching and knowledge retention. It solves problems of information loss and context fragmentation by providing gates, checkpoints, and context packs. Ideal for use in complex, multi-step tasks that require local deterministic memory management.

Canonical page: https://skillsregistry.net/skills/dev-ithz-ithz-mcp  
JSON: https://api.skillsregistry.net/v1/skills/dev-ithz-ithz-mcp

## Description

Local deterministic project memory for AI agents with context packs, gates and checkpoints.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.1.0a1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-06-20

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/dev.ithz%2Fithz-mcp)

## 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": "dev-ithz-ithz-mcp"
    }
  }
}
```

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