# io.github.masa-san-jp/aiko (npm · aiko-mcp)

A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `aiko-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/masa-san-jp-aiko/aiko-mcp.md), [page](https://verifymcp.io/servers/masa-san-jp-aiko/aiko-mcp)

## Channel facts

- Registry: `npm`
- Package: `aiko-mcp`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to masa-san-jp/Agent-Aiko).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 56/100
  - 78% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 611 tokens (~43/item across 14 items; 9 tools + 5 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add masa-san-jp-aiko -- npx -y aiko-mcp
```

### Codex

```bash
codex mcp add masa-san-jp-aiko -- npx -y aiko-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "masa-san-jp-aiko": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "aiko-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add masa-san-jp-aiko --command npx --arg -y --arg aiko-mcp
```

### Hermes

```yaml
mcp_servers:
  masa-san-jp-aiko:
    command: "npx"
    args: ["-y", "aiko-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "masa-san-jp-aiko": {
      "command": "npx",
      "args": [
        "-y",
        "aiko-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-04 (score 69, +39)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Schema quality: unverified → 78
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.07
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: poor
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 0

### 2026-08-03 (score 30, −15)

- [security regression] Malware scan: pass → unverified
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Schema quality: unverified → 78
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: poor
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 0
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-08-02 (score 45)

First indexed and scored.

## MCP tools (9)

### `aiko.bind_runtime` (~76 tokens)

Runtime Profile を合成する

人格・ユーザー・能力を合成して Runtime Profile を作る。合成できない場合は理由を返し、Profile は返さない（fail closed）

Input parameters:

- `capabilityManifest`
- `injectionMethod` (string)
- `outputPrefix` (string)
- `runtime` (string, required)

### `aiko.get_runtime_profile` (~57 tokens)

合成済みの Runtime Profile を取得する

profile_id を省略すると直近のものを返す。instructions 本文を含めるかは includeInstructions で選ぶ

Input parameters:

- `includeInstructions` (boolean)
- `profileId` (string)

### `aiko.remember_user` (~90 tokens)

呼び名や記憶の場所を覚える

ユーザーが「〇〇と呼んで」「記憶は〇〇にある」と言ったときに使う。~/.aiko/user.md へ書く。記憶は場所を控えるだけで、中身は読まない

Input parameters:

- `address` (string)
- `memory` (string)
- `name` (string)

### `aiko.list_personas` (~41 tokens)

使える人格の一覧を返す

オリジナルと、ユーザーが作った人格を返す。いまどれを使っているかも分かる

### `aiko.switch_persona` (~60 tokens)

使う人格を切り替える

ユーザーが「〇〇に切り替えて」「オリジナルに戻して」と言ったときに使う。origin を指定するとオリジナルへ戻る

Input parameters:

- `name` (string, required)

### `aiko.save_persona` (~63 tokens)

独自の人格を保存する

ユーザーが人格を作りたい・書き換えたいときに使う。origin は書き換えられないので別名で保存する

Input parameters:

- `content` (string, required)
- `name` (string, required)

### `aiko.delete_persona` (~53 tokens)

独自の人格を消す

ユーザーが消してと言ったときだけ使う。使用中の人格を消す場合はオリジナルへ戻してから消す

Input parameters:

- `name` (string, required)

### `aiko.report_capabilities` (~52 tokens)

Capability Manifest を解釈する

使える能力と、使えない能力（理由つき）に分ける。認証情報の値を含む宣言は拒否する

Input parameters:

- `capabilityManifest` (required)

### `aiko.health` (~31 tokens)

サーバーと人格の状態を返す

人格を読めているか、Profile をいくつ保持しているかを返す

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/masa-san-jp-aiko/aiko-mcp#diagnostics

## Score history

- 2026-08-04: 69
- 2026-08-03: 30
- 2026-08-02: 45

## Links

- npm package: https://www.npmjs.com/package/aiko-mcp
- Socket report: https://socket.dev/npm/package/aiko-mcp
- Repository: https://github.com/masa-san-jp/Agent-Aiko
- Changelog RSS feed: https://verifymcp.io/servers/masa-san-jp-aiko/aiko-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/masa-san-jp-aiko/aiko-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/masa-san-jp-aiko/aiko-mcp