Deputy

Name: Deputy
Author: alimohammadiamirhossein

作者：alimohammadiamirhosseinバージョン 0.3.1i★ –iパソコンで動く

レジストリ名io.github.alimohammadiamirhossein/deputy

インストール

概要

作者による説明（英語の原文）

Claude Code helper: DeepSeek V4.1 Flash reviews Claude's code for bugs and gives second opinions

PopNx MCPの3つの柱

この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。

利用者の声iレビューはまだありませんレビューは今後のステップで、アカウント機能と一緒に始まります
私たちの基本チェックi1項目中1項目に合格公開情報からチェック。コードはまだスキャンしていません
利用状況iとても新しい↓ 46/週 · ★ –

できること

このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。

接続方法: パソコンで動く
トランスポート: stdio
カテゴリ: 開発者ツール
入力が必要なもの：DEEPINFRA_API_KEY, XAI_API_KEY, DEPUTY_API_KEY

インストール

使っているAIアプリを選んで、設定をコピーしてください。

インストールの前に

基本チェック：1項目中1項目に合格
あなたのパソコンで、あなたのユーザーと同じ権限（ファイル、ネットワーク、アプリ）で動きます。
自分で入力するもの： DEPUTY_PROVIDER, DEEPINFRA_API_KEY, XAI_API_KEY, DEPUTY_MODE, DEPUTY_THINKING, DEPUTY_MODEL, DEPUTY_BASE_URL, DEPUTY_WORKSPACE, DEPUTY_API_KEY

「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。

必要なもの

PyPIPythonのuvのインストール（uvxコマンドに必要）

どのアプリを使っていますか？

ClaudeClaude CodeCursorVS CodeChatGPT

上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。

Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます

{
  "mcpServers": {
    "deputy": {
      "command": "uvx",
      "args": [
        "deputy-cc",
        "serve"
      ],
      "env": {
        "DEPUTY_PROVIDER": "your-value",
        "DEEPINFRA_API_KEY": "your-value",
        "XAI_API_KEY": "your-value",
        "DEPUTY_MODE": "your-value",
        "DEPUTY_THINKING": "your-value",
        "DEPUTY_MODEL": "your-value",
        "DEPUTY_BASE_URL": "your-value",
        "DEPUTY_WORKSPACE": "your-value",
        "DEPUTY_API_KEY": "your-value"
      }
    }
  }
}

ターミナルでこれを実行します

claude mcp add deputy --env DEPUTY_PROVIDER=your-value --env DEEPINFRA_API_KEY=your-value --env XAI_API_KEY=your-value --env DEPUTY_MODE=your-value --env DEPUTY_THINKING=your-value --env DEPUTY_MODEL=your-value --env DEPUTY_BASE_URL=your-value --env DEPUTY_WORKSPACE=your-value --env DEPUTY_API_KEY=your-value -- uvx deputy-cc serve

動かす前に、空欄の値を入力してください。

Cursorで開く

または、設定を自分でコピーする

プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます

{
  "mcpServers": {
    "deputy": {
      "command": "uvx",
      "args": [
        "deputy-cc",
        "serve"
      ],
      "env": {
        "DEPUTY_PROVIDER": "your-value",
        "DEEPINFRA_API_KEY": "your-value",
        "XAI_API_KEY": "your-value",
        "DEPUTY_MODE": "your-value",
        "DEPUTY_THINKING": "your-value",
        "DEPUTY_MODEL": "your-value",
        "DEPUTY_BASE_URL": "your-value",
        "DEPUTY_WORKSPACE": "your-value",
        "DEPUTY_API_KEY": "your-value"
      }
    }
  }
}

ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。

VS Codeで開く

または、設定を自分でコピーする

プロジェクトの .vscode/mcp.json に貼り付けます

{
  "servers": {
    "deputy": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "deputy-cc",
        "serve"
      ],
      "env": {
        "DEPUTY_PROVIDER": "your-value",
        "DEEPINFRA_API_KEY": "your-value",
        "XAI_API_KEY": "your-value",
        "DEPUTY_MODE": "your-value",
        "DEPUTY_THINKING": "your-value",
        "DEPUTY_MODEL": "your-value",
        "DEPUTY_BASE_URL": "your-value",
        "DEPUTY_WORKSPACE": "your-value",
        "DEPUTY_API_KEY": "your-value"
      }
    }
  }
}

これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。

選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。

自分で入力する値

DEPUTY_PROVIDER env
deepinfra (DeepSeek V4.1 Flash) or xai (Grok, default model grok-4.3).
DEEPINFRA_API_KEY 秘密 env
DeepInfra API key (deepinfra.com, Dashboard > API Keys), for the default provider. Only sent to api.deepinfra.com.
XAI_API_KEY 秘密 env
xAI API key (console.x.ai), when DEPUTY_PROVIDER is xai. Only sent to api.x.ai.
DEPUTY_MODE env
accuracy: Claude writes all code; Deputy reviews and consults. lean: fewest Claude tokens, little accuracy loss. balanced: Deputy takes mechanical work. partner: Deputy does all low-level work and gi…
DEPUTY_THINKING env
How hard the helper model thinks.
DEPUTY_MODEL env
Model id served by the endpoint.
DEPUTY_BASE_URL env
Any OpenAI-compatible endpoint (https, or http on localhost for a local model).
DEPUTY_WORKSPACE env
Project folder Deputy may read and edit. Defaults to the client's project folder.
DEPUTY_API_KEY 秘密 env
API key for a non-DeepInfra endpoint. Takes precedence over DEEPINFRA_API_KEY.

この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。

できること

パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。

基本チェックi

誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月9日にチェック

✓ 合格
作者とリポジトリが一致
レジストリ名は、リポジトリを所有するGitHubアカウント alimohammadiamirhossein で確認済みです
… 未チェック
今もメンテナンスされている
このリポジトリはまだGitHubから読み取っていません
… 未チェック
ライセンスがある
このリポジトリはまだGitHubから読み取っていません
– 対象外
エンドポイントが応答する
これはパソコンで動くため、インターネット上のエンドポイントはありません
– 対象外
OAuthでサインイン
パソコンで動き、代わりにローカルの設定を使います
… 未チェック
ツールの説明に隠れた指示がない
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです

開発者ツールのほかのサーバーとの比較i

このカテゴリのほかの5558件のうち0%よりスターが多い
このカテゴリのほかの5558件のうち66%より最近レジストリに公開
基本チェックの結果が、このカテゴリのほかの5558件のうち100%と同じかそれ以上

レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。

よくある質問

Deputyは安全ですか？

当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。

どんなキーやコードが必要ですか？

入力が必要なもの：DEEPINFRA_API_KEY, XAI_API_KEY, DEPUTY_API_KEY

パソコンで動きますか、それともクラウドですか？

あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません（サーバー自体がオンラインサービスを呼び出す場合を除きます）。

今もメンテナンスされていますか？

GitHubリポジトリの最終更新は–、最新バージョン（0.3.1）がレジストリに届いたのは13 日前です。

どのアプリで使えますか？

Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。

代わりに使えるものは？

同じカテゴリには：GitHub, Desktop Commander, Cloudflare MCP

代わりの候補

同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。

カードの見方：↓ 週あたりのダウンロードi★ GitHubスターi3つの柱：レビュー · チェック · 利用状況i更新＝最新バージョンをレジストリに公開した日i

GitHub

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

作者：github広く使われている★ 3.4万5 日前更新

パソコンでもクラウドでも

インストール

Desktop Commander

MCP server for terminal commands, file operations, and process management

作者：wonderwhy-er広く使われている↓ 71万/週★ 1万17 日前更新

パソコンで動く

インストール

Cloudflare MCP

Cloudflare MCP servers

作者：cloudflare広く使われている★ 444614 か月前更新

クラウドで動く✓ mcp.cloudflare.com

インストール

作者のREADME

READMEを開く

作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。

Deputy

Deputize cheap models. Claude stays the sheriff.

Deputy is a Claude Code plugin and MCP server that has a cheap model, DeepSeek V4.1 Flash, review Claude's code for bugs and give second opinions, for under a cent each. Claude keeps writing the code.

A replay of one benchmark case. Deputy's findings, time and cost, the repro and the test run are real.

claude plugin marketplace add alimohammadiamirhossein/deputy

claude plugin install deputy@deputy

Inside Claude Code the same thing is /plugin marketplace add alimohammadiamirhossein/deputy. You need uv and a DeepInfra API key.

What it costs (measured)

Run	Time	Cost
`review`: two reviewers check a change with a planted off-by-one bug (both caught it)	27 s	$0.0011
`consult`: second opinions from 2 angles	68 s	$0.0018
`investigate`: list a project's functions and their tests	18 s	$0.0004
`delegate`: fix a bug, add 3 tests, run pytest until green	46 s	$0.0006

Measured on a small demo project with thinking high. Reviews and second opinions now think at low by default, which makes them faster and cheaper (see the review benchmark below). On real projects, expect consult and review to stay under $0.01. Every result shows its real tokens and cost.

Benchmark: Opus with and without Deputy

Four small Python tasks with hidden tests Claude never sees (bench/), one run each on Claude Opus 5.5, October 2026. These runs predate the faster reviews: reviewers then thought at high with no time limit, and the prompt asked Claude to review every task.

Config	Hidden tests passed	Mean cost (Claude + Deputy)	Median time
Opus alone	4/4	$0.18	30 s
Opus + `/deputy:review`	4/4	$0.31 ($0.30 + $0.013)	3.7 min
Opus + `/deputy:delegate`	4/4	$0.19 ($0.19 + $0.0015)	76 s

What this shows, and what it doesn't:

No accuracy gain to measure here. The tasks are too easy: Opus passed every hidden test on its own.
Reviews cost Claude more than they cost Deputy. Deputy's share is about a cent, but Claude spends more checking the findings, so a reviewed task cost 68% more and took longer. One review took 24 minutes because a reviewer thought for 73k tokens. Reviewers now think at low and stop after 180 s, and Claude reviews only risky or large changes.
The findings still changed the code. In 3 of 4 tasks Claude hardened the code beyond the spec: it fixed a rate limiter that a NaN timestamp would block forever, and added missing tests. It rejected one finding that contradicted the spec.
Delegating saved nothing on tasks this small. Claude's own reading and checking cost about as much as writing the code itself.
Small sample. One run per config. Full table: bench/results/2026-10-24-opus.

Does `review` catch bugs, and how often does it cry wolf?

Deputy's review on its own, without Claude, on 6 changes with a planted bug and 8 clean changes. Each planted bug has a clean twin, the same change done right. Five runs each with the default settings (bench/review_cases):

Diffs	Reviews	Flagged	Flagged major or critical	Mean cost	Median time	Slowest
Planted bug	30	30/30 caught	30/30	$0.0016	28 s	59 s
Clean	40	22/40	10/40	$0.0039	80 s	230 s

Every planted bug was caught, at major or critical severity, by both reviewers every time.
Reviews are quick. Reviewers think at low and stop after 180 s. With high thinking and no cap they caught the same bugs, but the median clean review took 160 s and the slowest 23 minutes.
Clean code still draws findings, so Claude has to check each one. Most are minor (36 of 50), but a quarter of clean reviews included a major claim.
Many of those findings are fair, such as a test that can't fail, an entry point no test covers, or a cache key wider than the change assumed.
The benchmark already fixed one cause of false alarms. In the first run, reviewers read new files labelled "(untracked)" as left out of the change. Deputy now shows them as git diff does, and those findings went from 6 to 0.
Agreement is weak evidence on clean code. Both reviewers flagged the same spot on 20% of clean diffs, so a finding isn't real just because two reviewers report it.
Every finding on a clean diff is listed in the results: default settings, high thinking, no cap, first run.

What it does

Claude (for example Opus 5.5) stays in charge and writes the code. Deputy adds four tools that run a much cheaper model as a helper inside your project:

Tool	What it does
`review`	Independent reviewers hunt for bugs in a risky or large change before Claude calls it done
`consult`	Second opinions from 2–4 angles at once, before Claude commits to a plan
`investigate`	Reads lots of code and returns `file:line` leads
`delegate`	Hands a coding task to the cheap model (off by default; on request, or in savings mode)
`stats`	Shows roughly how many tokens and dollars Deputy saved: this session, today, this week, all time

Claude treats everything Deputy says as an unverified hint: it checks each finding against the code and keeps only what holds up.

See what you saved

Every result ends with a one-line estimate, for example from a real investigate run:

Savings (rough): this work would cost about $0.0082 on Claude Opus 5.5; Deputy did it for $0.0001. Saved about $0.0074 and 2.0k Claude Opus 5.5 tokens.

Ask Claude for stats, or run deputy stats, for totals. Reviews and second opinions are listed separately as extra checks, so they never inflate the savings. The estimate assumes your lead model would use about as many tokens, so treat it as an order of magnitude. Only numbers are stored, never code or prompts. Set your lead model with DEPUTY_LEAD_MODEL (opus, sonnet, haiku, fable or custom).

When to use Deputy, and when not to

Use it for:

Risky or large changes, where a missed bug costs more than a minute of waiting: tricky logic, security, data handling, concurrency, refactors that touch several files.
A second opinion before Claude commits to a design, without spending Claude tokens on it.
Wide reading in a big codebase, such as "where is this setting read?".
Well-specified mechanical work (boilerplate, renames, test scaffolding) in lean, balanced, partner or savings mode, when you want to save Claude tokens on larger jobs. On small tasks it saved nothing in the benchmark.

Skip it for:

Routine changes whose tests pass, and trivial edits like typos and one-liners. A review makes you wait and adds little there.
Code you may not share with a third party. Deputy sends code to DeepInfra, or to whatever endpoint you set in DEPUTY_BASE_URL (a local model works too).
Final answers. Findings come from a weaker model and include false positives, which is why Claude verifies every one.
Architecture and security-sensitive decisions in savings mode. Keep those with Claude.

Quick start

1. Get a DeepInfra API key (DeepInfra hosts DeepSeek's models in the US)

Sign up at [deepinfra.com](https://deepinfra.com/) with GitHub, Google or email.
In Dashboard → Billing, add a card and $5–10 of credit, then set a spending limit equal to that amount.
In API Keys, create a key (it starts with sk-di-) and copy it. Keep it private.

You don't need a plan, a model purchase or a dedicated GPU. Pay-as-you-go credit is enough.

2. Install uv and the plugin

claude plugin marketplace add alimohammadiamirhossein/deputy

claude plugin install deputy@deputy

Claude Code asks for your DeepInfra key and stores it in your system's secure storage.

3. Restart Claude Code and try it

/deputy:review

/deputy:consult I plan to cache sessions in Redis. What am I missing? /deputy:investigate how does a request reach the database? /deputy:ds add input validation to the signup form, with tests

Or just work normally: Claude calls Deputy on its own when it pays off, and skips reviews on routine changes whose tests pass.

Cursor and Codex

One command adds Deputy to the editor's MCP config (with a backup of the old file) and installs the playbook as a Cursor rule or Codex skill:

uvx --from git+https://github.com/alimohammadiamirhossein/deputy deputy setup cursor --project .

uvx --from git+https://github.com/alimohammadiamirhossein/deputy deputy setup codex

Set DEEPINFRA_API_KEY in your environment first, then restart the editor. Add --dry-run to see the changes without writing them. Ready-made files are in integrations/.

Grok instead of DeepSeek (experimental, not tested yet): Grok support follows xAI's documentation but has not been run with a real xAI key. If you try it, please tell us what worked and what didn't, even if it was just a one-word "works". Add --provider xai and set XAI_API_KEY (from console.x.ai) instead. Deputy then uses grok-4.3; set DEPUTY_MODEL to grok-build-0.1 (xAI's coding model) or grok-4.7 (its strongest). Grok costs about 10 times more per token than DeepSeek V4.1 Flash.

uvx --from git+https://github.com/alimohammadiamirhossein/deputy deputy setup cursor --project . --provider xai

Other MCP clients (Cline, Windsurf, Claude Desktop)

Deputy is on PyPI as deputy-cc. Add a stdio MCP server that runs:

uvx deputy-cc serve

with DEEPINFRA_API_KEY set in its environment. Check your setup with uvx deputy-cc doctor.

Recommended model: DeepSeek V4.1 Flash, thinking

冒頭だけを表示しています。続きはリポジトリで読めます

Deputy

概要

PopNx MCPの3つの柱

できること

インストール

インストールの前に

自分で入力する値

できること

基本チェックi

作者とリポジトリが一致

今もメンテナンスされている

ライセンスがある

エンドポイントが応答する

OAuthでサインイン

ツールの説明に隠れた指示がない

開発者ツールのほかのサーバーとの比較i

よくある質問

代わりの候補

GitHub

Desktop Commander

Cloudflare MCP

作者のREADME

Deputy

Deputize cheap models. Claude stays the sheriff.

What it costs (measured)

Benchmark: Opus with and without Deputy

Does review catch bugs, and how often does it cry wolf?

What it does

See what you saved

When to use Deputy, and when not to

Quick start

Cursor and Codex

Other MCP clients (Cline, Windsurf, Claude Desktop)

Recommended model: DeepSeek V4.1 Flash, thinking

Does `review` catch bugs, and how often does it cry wolf?