PlanWright

tools.planwright由 planwright.tools 發布官方發布者v1.0.2更新於 Oct 24, 2026

Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.

已驗證Streamable HTTP可網頁執行效率與工作流開發者工具

概覽

AI 產生的概覽

Planwright 是託管的規劃看板：人類設定目標，編碼代理透過 MCP 認領、拆解、執行並回報工作，全程留下簽章稽核紀錄。

可以做什麼
  • 工作階段設定：選擇目前儲存庫或專案，列出工作區與專案，讀取、上傳或列出 CLAUDE.md、規格與架構文件等情境檔案。
  • 管理倡議（initiative）：列出、建立、更新與刪除工作區里程碑。
  • 管理目標：依泳道列出目標，檢視含執行歷程的詳細資料，建立附驗收條件的目標，更新並排程。
  • 代理工作流程：認領目標、提交拆解計畫、檢查對齊、記錄差異與測試結果、申請驗收、附加備註並標記清晰度問題。
  • 補充與分類：列出缺少意圖摘要或策略分類的目標，以及專案缺陷清單。
適用情境
適合想讓 Claude Code、Cursor、Codex 等編碼代理從共用目標看板領取工作、而非臨時下提示的情況，並需要可複核的代理計畫、變更與測試紀錄。
執行需求
需要連線至 mcp.planwright.tools 的遠端 Streamable HTTP 端點，無須自架或本機安裝。使用 OAuth 2.1 與動態用戶端註冊，首次連線時在瀏覽器以 GitHub 登入；CI/CD 或無介面環境可在設定中產生靜態權杖。需要一個已連結 GitHub 的專案。
安裝前請注意
需要 GitHub 帳號登入或靜態 MCP 權杖，可存取你的看板。代理可建立、更新與刪除倡議和目標，並可上傳或覆寫情境檔案，會改變共用專案狀態。差異、測試結果與情境檔案會上傳到第三方託管服務。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 PlanWright，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/tools.planwright%2Fplanwright/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "planwright": {
      "type": "http",
      "url": "https://mcp.planwright.tools/mcp"
    }
  }
}

README

Planwright

Control plane for autonomous software labor.

Planwright is the objective-native planning board for agent-led software development. Humans define outcomes at the Objective layer; coding agents (Claude Code, Cursor, Codex, and others) claim work, decompose tasks, execute, and report back via native MCP—with every state change captured in a hash-chained, Ed25519-signed audit trail.

[Documentation] [MCP]

Quick Start

Claude Code (recommended)

bash
claude mcp add planwright https://mcp.planwright.tools/mcp

Your browser opens for GitHub login. That's it.

Other Agents

See the full agent setup guides for Cursor, Codex, Claude Desktop, and generic MCP clients.

How It Works

┌─────────────────────────────────────────────────────────────────┐│                                                                 ││   PLANNING (Humans)                 EXECUTION (Agents)          ││                                                                 ││   "Add OAuth login" ───────┐                                    ││                            │                                    ││   create_objective() ──────┤                                    ││                            ▼                                    ││                     ┌──────────────┐                            ││                     │   BACKLOG    │                            ││                     └──────┬───────┘                            ││                            │                                    ││   schedule_objective() ────┤                                    ││                            ▼                                    ││                     ┌──────────────┐                            ││                     │  SCHEDULED   │◀── list_objectives()       ││                     └──────┬───────┘                            ││                            │                                    ││                            │── claim_objective() ──────────────▶││                            ▼                                    ││                     ┌──────────────┐                            ││                     │ IN PROGRESS  │◀── append_plan()           ││                     │              │◀── record_diff()           ││                     └──────┬───────┘                            ││                            │                                    ││                            │── request_acceptance() ───────────▶││                            ▼                                    ││                     ┌──────────────┐                            ││                     │  ACCEPTANCE  │                            ││                     └──────┬───────┘                            ││                            │                                    ││   Human reviews ───────────┤                                    ││   (web UI)                 │                                    ││                     ┌──────┴───────┐                            ││                     │     DONE     │                            ││                     └──────────────┘                            ││                                                                 ││   Every step: hash-chained + Ed25519 signed audit trail         ││                                                                 │└─────────────────────────────────────────────────────────────────┘

Key Features

Objective-Native, Not Task-Based No story points. No velocity charts. No capacity planning. Agents decompose objectives into tasks themselves—you manage outcomes, not effort.

Immutable Audit Trail Every state change produces a hash-chained, Ed25519-signed audit record. Know exactly what the agent planned, what it changed, and when.

Native MCP Integration Agents connect via the Model Context Protocol—no custom API clients needed. Works with any MCP-compatible agent.

Multi-Agent Support Claude Code, Cursor, Codex, Factory, Amp—if it speaks MCP, it can work from your Planwright board.

Context Files Push CLAUDE.md, architecture docs, and specs to Planwright. Agents read them before starting work.

Documentation

Examples

See the examples/ directory for:

  • Sample CLAUDE.md files for different project types
  • Example objective structures
  • Context file templates

MCP Server

Planwright's MCP server is hosted and managed—no self-hosting required.

EndpointProtocol
https://mcp.planwright.tools/mcpStreamable HTTP

Authentication is handled via OAuth 2.1 with Dynamic Client Registration (RFC 7591). Your agent opens a browser for GitHub login on first connection.

For CI/CD and headless environments, generate a static token in Settings → MCP Tokens.

Available Tools

Planwright exposes 30 MCP tools for agent orchestration:

Setup & Context

ToolDescription
planwright_set_repoSet active project for the session (by GitHub repo or project ID)
planwright_list_workspacesList workspaces you have access to
planwright_list_projectsList projects with IDs and linked GitHub repos
planwright_list_context_filesList CLAUDE.md, specs, architecture docs for the project
planwright_get_context_fileRead a specific context file
planwright_push_context_fileUpload or update a context file
planwright_get_doc_suggestionsGet pending documentation gap suggestions
planwright_dismiss_doc_suggestionDismiss a doc suggestion
planwright_get_board_urlGet the Planwright board URL

Initiatives

ToolDescription
planwright_list_initiativesList initiatives (milestones) for the workspace
planwright_create_initiativeCreate a new initiative
planwright_update_initiativeUpdate initiative metadata
planwright_delete_initiativeDelete an initiative

Objectives

ToolDescription
planwright_list_objectivesList objectives by lane (backlog, scheduled, in_progress, acceptance, done)
planwright_get_objectiveGet full objective details including agent run history
planwright_create_objectiveCreate a new objective with acceptance criteria
planwright_update_objectiveUpdate objective metadata
planwright_schedule_objectiveMove objective from backlog to scheduled

Agent Workflow

ToolDescription
planwright_claim_objectiveClaim a scheduled objective and start an agent run
planwright_append_planPost the agent's decomposition plan
planwright_check_alignmentVerify work aligns with claimed objective (drift detection)
planwright_record_diffRecord diff summary and test results
planwright_submit_test_runSubmit acceptance criteria verification results
planwright_request_acceptanceMove objective to acceptance lane for human review
planwright_append_noteRecord task completion in the agent run log
planwright_flag_clarityFlag objective as having clarity concerns
planwright_override_clarityHuman override for clarity flags

Enrichment & Classification

ToolDescription
planwright_list_unenrichedList objectives/initiatives missing intent summaries
planwright_list_unclassifiedList objectives missing strategic classification
planwright_list_my_bugsList bugs for this project

Support

License

Planwright is a commercial product. The MCP integration examples in this repository are provided under the MIT License.

See LICENSE for details.

來源：README.md，提交 a7b1106

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v1.0.2最新Sep 16, 2026

評分

已滿足適用檢查項的 75%

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 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 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

    請在儲存庫或註冊中心條目中宣告授權條款。