
junai Pipeline MCP
io.github.saajunaid由 GitHub 帳號 saajunaid 發布v0.1.1更新於 Oct 24, 2026
Agentic pipeline orchestration MCP server for AI-driven development workflows.
概覽
在本機執行代理式開發流程,規劃功能、依階段實作,並產生工作階段交接記錄。
- 可以做什麼
- 這是一個面向 AI 驅動開發工作流程的代理式流程編排伺服器。它支援分階段、測試驅動的功能規劃,依階段實作並逐階段提交,對程式碼差異進行跨廠商審查,並產生工作階段交接文件。它也提供分層記憶模型,以及防止寫入密鑰或執行破壞性操作的鉤子。
- 適用情境
- 當你希望 AI 助理在程式碼儲存庫中,把一項軟體功能從規劃推進到實作與審查,並在不同工作階段之間無須重新摸索即可繼續時,可以使用它。
- 執行需求
- 以本機程序在使用者機器上執行,透過 stdio 從 PyPI 套件 junai-mcp 安裝。需要 PATH 中有 Python 3.11 或更新版本,以及用來讀取儲存庫狀態的 Git。選用環境變數 JUNAI_WORKSPACE_ROOT 與 PIPELINE_STATE_PATH 分別設定工作區根目錄與流程狀態檔。DeepSeek 或 GLM 的 API 金鑰為選用,僅用於跨廠商審查。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 junai Pipeline MCP,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
caddis — a Claude Code harness
Browse every command, skill, agent and hook -> saajunaid.github.io/caddis-plugin — the reference site, rebuilt on every publish.
caddis is a Claude Code harness — a plugin (plus a shared pool of skills, subagents,
slash-commands, and hooks) that makes a single Claude Code session dramatically more capable and much
harder to derail. It's agent-agnostic: the same pool is exported to other AI CLIs (Codex,
Antigravity, Copilot), and CLAUDE.md↔AGENTS.md are mirrors so every agent reads the same
conventions.
Before you start
Honest about the platform: caddis is developed and used daily on Windows with PowerShell.
The hooks are pure Python and cross-platform, and the skills, commands and agents are plain markdown
that work anywhere — but some launchers ship as both .ps1 and .sh, the deployment skill is
Windows-specific, and the publishing machinery (sync.ps1) is PowerShell-only. Nothing here is
hostile to macOS or Linux; it is simply less travelled, so expect rough edges and please report them.
Your first five minutes
Then, in a Claude Code session, confirm it actually loaded:
If that prints a version, you are installed. From there, the shortest path to seeing what caddis is for:
Everything else is optional. If you only ever use feature-plan → implement → cross-review, you
have most of the value.
This repository is the published marketplace mirror: it hosts the caddis and caddis-extras
Claude Code plugins, the portable per-harness bundles under bundles/, and the shared pool. It is
generated and pushed by the caddis authoring repo's exporter — issues are welcome here, but code
changes land upstream and are synced in.
Install (Claude Code)
Then, in any repo:
A normal working loop looks like:
The one habit that matters most: end every session with /handoff. It writes
.caddis/relay.md, which is re-injected automatically at the next session start — you resume with
zero re-discovery instead of a cold, forgetful session.
See USERGUIDE.md for the full command/skill/hook reference and the mental models.
What you get
- Slash-commands —
/feature-plan,/prd,/implement,/tdd,/ship·/ship-pr·/ship-merge,/handoff,/kb,/digress·/resume,/cross-review,/usage-review,/mermaid-db·/excalidraw-db,/setup-project-ai,/migrate-dir. - Subagents — lean, own-context helpers:
anchor(evidence-first verification),code-reviewer,preflight(plan-vs-codebase validation),tester,debug,codebase-audit,security-analyst,data-engineer,sql-expert,knowledge-transfer. - A four-layer memory model — session relay (
relay.md), automatic Dream Memory (memory.jsonl), a per-repo knowledge base (.caddis/kb/+DOC-MAP.md), and cross-repo memory. - Hooks & safety — a PreToolUse guard for secret/destructive writes, auto-lint on edit, and the SessionStart/Stop hooks behind relay + memory.
- Tiered skills — the core dev set ships in
caddis; the long tail (cloud, data, media, productivity) lives incaddis-extras, off by default.
Installing outside Claude Code (Codex, Antigravity, …)
The knowledge layer (skills + AGENTS.md conventions) works in any harness. Per-harness bundles are
published under bundles/ and installed with caddis-init:
Safe by design: a sha256 manifest tracks what the installer wrote; re-runs update only unmodified files, and anything you edited locally is reported as a conflict, never overwritten.
Repo layout
A note on names
caddis was previously published as claudster (and, before that, this repo hosted the junai
Copilot pipeline — see the pre-1.2 entries in CHANGELOG.md). Repos set up under
the old name have a .claudster/ artifact dir; everything reads both .caddis/ and .claudster/
and writes where the repo already lives, so nothing breaks. Run /caddis:migrate-dir when you
want a repo converted. The ~/.claudster/ user scope (keys, install records) is permanent.
License
MIT. The published plugin bundles (caddis / caddis-extras) carry the same license
in their manifests.
來源:README.md,提交 2a72043
工具
0版本歷史
1- v0.1.1最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分