Spec Driven Development
제작자: formulahendry
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
내 컴퓨터에서 실행★ 440MIT14개월 전 업데이트
설치
Board Planner
개요
제작자가 쓴 설명(영어 원문)
Project board for teams and coding agents: Kanban, sprints, 46 tools, OAuth 2.1 or API tokens.
PopNx MCP의 세 기둥
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
- 사용자 의견i아직 리뷰가 없어요리뷰는 다음 단계에서 계정 기능과 함께 열려요
- 우리의 기본 점검i1개 중 1개 통과공개된 정보로 점검했으며, 코드는 아직 스캔하지 않았어요
- 사용 정도i아직 측정 안 함★ –
할 수 있는 일
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
- 연결 방식: 클라우드에서 실행
- 전송 방식: Streamable HTTP
- 카테고리: 기타
설치
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
설치하기 전에
- 기본 점검: 1개 중 1개 통과
- 제작자의 서버에서 실행돼요. 내가 요청한 내용은 제작자의 서버를 거쳐요.
- 레지스트리에 입력해야 할 키가 나와 있지 않아요.
필요한 것
- 클라우드에서 실행설치할 것 없음. 인터넷으로 연결돼요
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
- Settings → Connectors 열기
- Add custom connector 누르기
- 아래 주소를 붙여 넣고 Add 누르기
- 로그인하라고 하면 제작자의 서비스에 로그인하기
https://{organisation}.board-planner.com/api/mcp주소에 나만 아는 {…} 부분(예: 내 계정)이 있어서, 복사한 뒤 직접 채워 주세요.
터미널에서 이 명령어를 실행하세요
claude mcp add --transport http board-planner 'https://{organisation}.board-planner.com/api/mcp'주소에 나만 아는 {…} 부분(예: 내 계정)이 있어서, 복사한 뒤 직접 채워 주세요.
또는 설정을 직접 복사하기
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"board-planner": {
"url": "https://{organisation}.board-planner.com/api/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
주소에 나만 아는 {…} 부분(예: 내 계정)이 있어서, 복사한 뒤 직접 채워 주세요.
또는 설정을 직접 복사하기
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"board-planner": {
"type": "http",
"url": "https://{organisation}.board-planner.com/api/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
- 웹에서 ChatGPT 열기 → Settings → Connectors (Apps)
- Create 또는 Add 누르기(일부 요금제는 먼저 Advanced에서 Developer mode를 켜야 해요)
- 아래 주소를 붙여 넣고 이름을 정한 뒤 저장하기
- 로그인하라고 하면 제작자의 서비스에 로그인하기
https://{organisation}.board-planner.com/api/mcp주소에 나만 아는 {…} 부분(예: 내 계정)이 있어서, 복사한 뒤 직접 채워 주세요.
메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
할 수 있는 일
주소에 내 값이 필요해서 대신 도구 목록을 읽을 수 없어요.
기본 점검i
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
- ✓ 통과
제작자와 저장소 일치
레지스트리 이름이 GitHub 계정 rafalpodles 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
주소에 내 계정 값이 필요해서 대신 점검할 수 없어요
- – 해당 없음
OAuth로 로그인
주소에 내 계정 값이 필요해서 대신 점검할 수 없어요
- … 아직 점검 안 함
도구 설명에 숨겨진 지시 없음
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
기타 카테고리의 다른 서버와 비교i
- 이 카테고리의 다른 서버 32691개 중 0%보다 스타가 많아요
- 이 카테고리의 다른 서버 32691개 중 74%보다 최근에 레지스트리에 공개됐어요
- 기본 점검 결과가 이 카테고리의 다른 서버 32691개 중 100%와 같거나 더 좋아요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
자주 묻는 질문
Board Planner, 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?
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
아직 관리되고 있나요?
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.9.0)은 12일 전 레지스트리에 올라왔어요.
어떤 앱에서 쓸 수 있나요?
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
대신 쓸 수 있는 건 뭐가 있나요?
같은 카테고리에는: Spec Driven Development, Remote Desktop Commander, Dialyne
대안
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Remote Desktop Commander
제작자: desktop-commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
클라우드에서 실행★ 211그저께 업데이트
설치
Dialyne
제작자: dialyne
Real phone calls in France for AI agents: dial +33 numbers, menus, hold, AI disclosure.
클라우드에서 실행오늘 업데이트
설치
제작자의 README
README 열기
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Board Planner
One board. Your team works it. So do your agents.
A Kanban board, sprints and a dashboard small teams can actually run — plus an MCP server and a REST API, so coding agents pick up the same tasks under the same rules as everybody else.
Most trackers bolt automation on: a bot posts a comment, a script moves a card, and the real state of the work lives somewhere the board cannot see. Board Planner starts from the other end. The board, the REST API and the MCP server are three doors into one model, with the same permission checks behind each. An agent moving a task to *In Review* passes the same status rules as a person dragging the card, and leaves the same trail in the same history.
Cloud or self-hosted
In the cloud, signing up puts a new organisation on its own subdomain of board-planner.com. It starts with a 30-day Pro trial, no card, and then becomes Free — up to 10 members, unlimited projects and tasks, the REST API, the MCP server, and workers and agents on one machine — or Pro, which adds more members, any number of machines, a monthly AI allowance on our key and Coda sync. Agents, workers and API tokens never count as members.
On your own server, docker compose up gives you one organisation of your own. The Community edition is AGPL-3.0, has no member or machine limit and runs the AI features on your own key; Pro self-hosted adds Coda sync and e-mail support.
AI on your own key is free on every plan, and nothing that ships in Free will move to Pro. Prices and the full comparison are on board-planner.com/pricing.
Handing work to a machine
Plenty of tools can now make a machine write code. Board Planner is about everything around it: who proposed the work, who approved it, what the machine was allowed to touch, what had to pass before anything landed, and where it stops and gives the work back.
Two agents, at the two ends of that arc: a PM agent that proposes and writes things down, and an execution worker that takes an approved task and does it. Neither decides anything you did not let it decide.
A PM agent that brings you the decision
The PM agent is a project manager that lives in the project. It reads the board, notices what is stuck, duplicated or missing, and brings you the decision rather than filing a pile of tickets nobody asked for. It is good at the work nobody enjoys: writing the acceptance criteria a task was created without, finding the duplicate, saying where a sprint actually stands.
In that screenshot, the badge under the reply is the action — the message and the write are one record, so you can see a reply also changed ORB-9 rather than merely talking about it. And it left the task where it was, because it was told to. Board reviews run with change_status and create_task withheld, so the autonomous path can tell you something is wrong without quietly reorganising your board overnight.
It is off by default, per project, and metered rather than trusted: every call is counted in tokens per organisation, autonomous turns as well as yours, against an allowance an instance can set, and an instance administrator can lock it off for a project in a way project settings cannot override. Without OPENROUTER_API_KEY the pages say so and the feature stays inert; AI Assist runs on the same key.
📖 PM agent · Autonomous board reviews
You hand it over the way you would hand it to a person
Assign the task, name an agent, drag it into the column you approve from. That pair is the hand-over — nothing runs on a task that names no agent, and there is no falling back to a project default. A task somebody else assigned to you is a proposal, not a job queued on your machine.
An agent is a list of steps and gates
An agent is an ordered list of blocks, and there are exactly two kinds:
| Can it change anything? | Can it stop the run? | |
|---|---|---|
| Step — Implement, Push, Pull request, Merge | yes | no |
| Gate — Size, Protected files, Test written, Builds, Tests pass, Reviewed | no | yes |
A step cannot refuse and a gate cannot write, so every block that could stop the run is a gate, and you can see all of them at a glance.
Each step is its own model session. Two steps in one agent share the task and the worktree and nothing else, which is why *analyse, then implement* is different from asking one model to do both: the second step reads what the first wrote, not what it was thinking.
Merging is a step, not a switch. There is no "auto-merge" checkbox and no rule that ties it to a review setting. An agent merges because its sequence ends with a Merge block; leave it out and the run stops at the pull request.
Three agents ship with it: Default, With security review and Merges its own work. A project that never opens the editor runs Default.
The machine is not trusted, by construction
This is the part that took the longest to get right, and it is why the hand-over is safe to use on a real repository:
| Guarantee | Why it holds |
|---|---|
| The server never sends a path | An assignment names a task and a git remote. The worker resolves its own checkout from a file on its own machine, so where anything lives stays a local decision. |
| A read-only step cannot be talked into writing | Read only becomes a tool list the worker builds itself. It is not a thing the board can express, so no prompt typed into a task can grant write access. |
| A check the machine does not implement stops the run | A gate naming an unknown kind refuses rather than skipping — a missing check must never look like a check that passed. |
| Nothing executes the repo's own scripts unreviewed | The editor refuses a Builds or Tests-pass gate over a change that Protected files has not read first, so a script the agent just wrote cannot run before something checked whether it was allowed to write it. |
| The worker holds one credential, and never the database | It talks to the app over REST with a cpw_ credential registration minted. A box executing agent-written code has no business holding database credentials. |
| It pushes as an account you named | gh auth switch is global state on a developer machine, so the identity is pinned per worker rather than left to whatever somebody switched to last. |
| A held task refuses to move | While a run holds a task, a status change that would leave the column is refused with 409 through every writer — board, edit form, MCP, PM agent. Forcing past it is a person's gesture: any machine credential is refused. |
| Failure lands in front of a human | A usage limit returns the task with its attempt refunded; a crash spends one. A repeating failure runs out of retries and stops, instead of cycling forever. |
The whole run reports onto the task as it happens, so the task's comments are the run log — branch, edits, which gate said no, how much model quota is left. No side channel, no CI tab.
📖 The full story: Agents · Execution workers · worker/README.md
The rest of the board
It's a board first
Columns you name, in an order you choose. Each one is mapped to a role automation understands (backlog, approved, active, review, blocked, done), so renaming *Up next* to *Ready* breaks nothing. Any column with the review role is a stop sign for automation, where work waits for a person. Drag-and-drop board, list view, sprints, dependencies and subtasks, recurring tasks, and ⌘K search across every task from anywhere in the app.
It follows your system theme, and the whole app is built for both:
A task holds everything the work needs
Acceptance criteria that tick off one by one, dependencies, the pull request that closes it, custom fields you define per project, every comment and every change since it was created. Name a branch bp-8/dark-mode and the pull request finds its task on its own.
Your agents work the same board
Forty-six MCP tools over HTTP put the board in your terminal, so Claude Code reads the backlog, claims a task and moves it — through the same permissions a teammate gets. API tokens can be scoped to specific projects, and the scope is enforced centrally, so it holds for REST and MCP alike.
Enough to answer the Monday question
How you are doing, what is piling up, and whether you are finishing as fast as you are starting. Six charts, no spreadsheet.
The rest
Notifications in-app, by email, or to Slack and Discord — per user, per project, per event. Project audit trail. Webhooks, signed. GitHub and GitLab PR linking. Works on a phone.
Quick start
You need Docker with Compose 2.24 or newer — older Compose rejects the file's env_file entry even without a .env. Nothing else: no Node, no MongoDB, not even a clone.
curl -fsSLO https://raw.githubusercontent.com/rafalpodles/board-planner/main/docker-compose.ymldocker compose up -d
That runs the published image, ghcr.io/rafalpodles/board-planner, built for linux/amd64 and linux/arm64 on every release from 1.1.0 on — 1.0.x predates it and has no image. :latest is the newest release; pin one with BOARD_PLANNER_VERSION=1.2.3 in a .env next to the compose file. To upgrade, docker compose pull && docker compose up -d.
The compose file on main needs an image of 1.1.2 or later: it passes COOKIE_ALLOW_INSECURE=auto
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요