# mai-mcp

> mai-mcp — maikai-group-mai-mcp. Use this tool when you need to retain project knowledge and decisions for Claude Code and Codex, leveraging a persistent memory that stores lessons and code graphs locally. It solves problems of lost context and duplicated efforts by providing a centralized repository of project information. Ideal for collaborative coding projects using git, where a shared understanding of code history and evolution is crucial.

Canonical page: https://skillsregistry.net/skills/maikai-group-mai-mcp  
JSON: https://api.skillsregistry.net/v1/skills/maikai-group-mai-mcp

## Description

Persistent memory for each project, dedicated skills, and a shared board for Claude Code and Codex to work together. Code graph, Git history, and a local dashboard. MIT licensed.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-23

## Source

- **Source listing:** [GitHub](https://github.com/maikai-group/mai-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": "maikai-group-mai-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/maikai-group-mai-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/maikai-group-mai-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