# khwan-mcp

> khwan-mcp — khwanlabs-khwan-mcp. Use this tool when you need to enhance your project's memory and learning capabilities, capturing corrections and improvements in real-time and distilling them overnight, without requiring model calls at runtime. It provides a durable memory solution for Claude Code and MCP clients, allowing for efficient knowledge retention and updates. Ideal for projects that require continuous learning and improvement, with seamless integration with git.

Canonical page: https://skillsregistry.net/skills/khwanlabs-khwan-mcp  
JSON: https://api.skillsregistry.net/v1/skills/khwanlabs-khwan-mcp

## Description

Durable memory for Claude Code and any MCP client — a brain per project, corrections captured as they happen, distilled overnight. Zero model calls at runtime.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/khwanlabs/khwan-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": "khwanlabs-khwan-mcp"
    }
  }
}
```

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