프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. 리뷰와 계정 기능은 다음 단계에서 열려요.
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

Deputy

제작자: alimohammadiamirhossein버전 0.3.1i★ –i내 컴퓨터에서 실행
레지스트리 이름io.github.alimohammadiamirhossein/deputy

설치

개요

제작자가 쓴 설명(영어 원문)

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

PopNx MCP의 세 기둥

이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.

할 수 있는 일

이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.

  • 연결 방식: 내 컴퓨터에서 실행
  • 전송 방식: stdio
  • 카테고리: 개발자 도구
  • 입력해야 할 값: DEEPINFRA_API_KEY, XAI_API_KEY, DEPUTY_API_KEY

설치

쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.

설치하기 전에

  • 기본 점검: 1개 중 1개 통과
  • 내 컴퓨터에서 내 사용자 계정의 권한(파일, 네트워크, 앱)으로 실행돼요.
  • 직접 입력할 값: DEPUTY_PROVIDER, DEEPINFRA_API_KEY, XAI_API_KEY, DEPUTY_MODE, DEPUTY_THINKING, DEPUTY_MODEL, DEPUTY_BASE_URL, DEPUTY_WORKSPACE, DEPUTY_API_KEY

비밀로 표시된 값은 내 계정의 열쇠예요. 절대 다른 사람과 공유하거나 채팅에 붙여 넣지 마세요.

필요한 것

  • PyPIPython의 uv 설치(uvx 명령어용)

어떤 앱을 쓰세요?

위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.

Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요

{
  "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"
      }
    }
  }
}

터미널에서 이 명령어를 실행하세요

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

실행하기 전에 빈 값을 채워 주세요.

Cursor에서 열기

또는 설정을 직접 복사하기

프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요

{
  "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"
      }
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

VS Code에서 열기

또는 설정을 직접 복사하기

프로젝트의 .vscode/mcp.json에 붙여 넣으세요

{
  "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"
      }
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.

선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.

직접 입력할 값

  • DEPUTY_PROVIDER env
    deepinfra (DeepSeek V4.1 Flash) or xai (Grok, default model grok-4.3).
  • DEEPINFRA_API_KEY 비밀 env
    DeepInfra API key (deepinfra.com, Dashboard > API Keys), for the default provider. Only sent to api.deepinfra.com.
  • XAI_API_KEY 비밀 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 비밀 env
    API key for a non-DeepInfra endpoint. Takes precedence over DEEPINFRA_API_KEY.

이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.

할 수 있는 일

내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.

기본 점검i

누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 8일 점검

  • ✓ 통과

    제작자와 저장소 일치

    레지스트리 이름이 GitHub 계정 alimohammadiamirhossein 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요

  • … 아직 점검 안 함

    계속 관리되고 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • … 아직 점검 안 함

    라이선스 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • – 해당 없음

    엔드포인트 응답

    내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요

  • – 해당 없음

    OAuth로 로그인

    내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요

  • … 아직 점검 안 함

    도구 설명에 숨겨진 지시 없음

    내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요

개발자 도구 카테고리의 다른 서버와 비교i

  • 이 카테고리의 다른 서버 4937개 중 0%보다 스타가 많아요
  • 이 카테고리의 다른 서버 4937개 중 75%보다 최근에 레지스트리에 공개됐어요
  • 기본 점검 결과가 이 카테고리의 다른 서버 4937개 중 100%와 같거나 더 좋아요

레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.

자주 묻는 질문

Deputy, 안전한가요?

해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.

어떤 키나 코드가 필요한가요?

입력해야 할 값: DEEPINFRA_API_KEY, XAI_API_KEY, DEPUTY_API_KEY

내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?

내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).

아직 관리되고 있나요?

GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.3.1)은 12일 전 레지스트리에 올라왔어요.

어떤 앱에서 쓸 수 있나요?

Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Python (uv)도 있어야 해요.

대신 쓸 수 있는 건 뭐가 있나요?

같은 카테고리에는: GitHub, Desktop Commander, Cloudflare MCP

대안

같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.

카드 보는 법:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i

GitHub

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

제작자: github널리 사용됨★ 3.4만5일 전 업데이트

컴퓨터 또는 클라우드

Desktop Commander

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

제작자: wonderwhy-er널리 사용됨↓ 71만/주★ 1만17일 전 업데이트

내 컴퓨터에서 실행

Cloudflare MCP

Cloudflare MCP servers

제작자: cloudflare성장 중★ 4.4천14개월 전 업데이트

클라우드에서 실행✓ mcp.cloudflare.com

제작자의 README

README 열기

제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.

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)

RunTimeCost
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 angles68 s$0.0018
investigate: list a project's functions and their tests18 s$0.0004
delegate: fix a bug, add 3 tests, run pytest until green46 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.

ConfigHidden tests passedMean cost (Claude + Deputy)Median time
Opus alone4/4$0.1830 s
Opus + /deputy:review4/4$0.31 ($0.30 + $0.013)3.7 min
Opus + /deputy:delegate4/4$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):

DiffsReviewsFlaggedFlagged major or criticalMean costMedian timeSlowest
Planted bug3030/30 caught30/30$0.001628 s59 s
Clean4022/4010/40$0.003980 s230 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:

ToolWhat 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)

  1. Sign up at [deepinfra.com](https://deepinfra.com/) with GitHub, Google or email.
  2. In Dashboard → Billing, add a card and $5–10 of credit, then set a spending limit equal to that amount.
  3. 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

앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요

PopNx에게 묻기