# Kirok

> Use this tool when you need to retain information across conversations and provide AI agents with a persistent memory. Kirok solves the problem of knowledge loss between interactions, enabling agents to recall and reflect on previous information. It takes in conversational data as input and outputs searchable, retained knowledge for future reference.

Canonical page: https://skillsregistry.net/skills/tadfuji-kirok-mcp  
JSON: https://api.skillsregistry.net/v1/skills/tadfuji-kirok-mcp

## Description

Provides persistent, searchable memory for AI agents, enabling them to retain, recall, and reflect on information across conversations.

## Trust

- **Trust score (0–1):** 0.21
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/kf4ad5xthn)
- **Repository:** <https://github.com/TadFuji/kirok-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": "tadfuji-kirok-mcp"
    }
  }
}
```

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