Keystone

pro.keystone-core由 keystone-core.pro 發布官方發布者v1.0.0更新於 Nov 11, 2026

C4 architecture model of your system, built from code by your AI and read back as focused context.

已驗證Streamable HTTP可網頁執行知識與記憶開發者工具

概覽

AI 產生的概覽

Keystone 維護軟體的 C4 架構模型,由 AI 助理從程式碼建構,並作為聚焦脈絡讀回給助理。

可以做什麼
  • 搜尋、讀取與遍歷架構模型:依名稱尋找元素與資料表,取得整體模型或單一模組,檢視相依關係與呼叫路徑
  • 分析某項變更的影響範圍,並只取得自某個模型版本以來的變動
  • 找出架構反模式,並回報針對程式碼的驗證結果與反模式發現
  • 以分支形式提出模型變更供人工審查,並執行提示詞來建構架構、描述容器或資料庫、追蹤情境、記錄決策以及與提交同步
  • 支援匯出為 PNG、SVG、Mermaid Markdown、Structurizr DSL 與 Obsidian 筆記,並可匯入 Structurizr 工作區
適用情境
適合助理在架構已記錄於 Keystone 的程式碼庫上工作、需要針對性脈絡而非整個模型時使用;也適合希望架構圖隨程式碼變更保持同步並以分支方式審查的情境。
執行需求
遠端 Streamable HTTP 端點,需在 Authorization 標頭提供 bearer 權杖,權杖於專案的 AI assistant → Connection 中建立。僅支援本機 stdio 伺服器的用戶端需透過 mcp-remote 橋接並安裝 Node.js。需要 Keystone 帳號與專案;託管服務提供有限額度的免費方案。
安裝前請注意
權杖依其擁有者在專案中的目前角色授權,檢視者角色的權杖只能讀取。模型變更以提案形式送出並產生分支,合併前需人工審查。README 稱原始碼不會傳送給 Keystone,但模型及由程式碼推導的資訊會存放在託管服務上;企業可選擇自架。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Keystone,將其新增到工作區。
  2. 連接 Authorization token 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/pro.keystone-core%2Fkeystone/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。

{
  "mcpServers": {
    "keystone": {
      "type": "http",
      "url": "https://keystone-core.pro/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Keystone

Understand your system before you change it.

Keystone keeps a C4 model of your software: systems, services, components with their public API, databases down to tables and columns, scenarios and architecture decisions. Your AI coding assistant builds the model from the code in your environment, keeps it in step with the code and reads it back over MCP as context for its next task. Every change arrives as a branch that your team reviews.

This repository holds no source code: it is the public home of Keystone for its MCP server, docs links and feedback.

[The Keystone editor: a service with its components and labelled relationships]

What it does

  • Builds the architecture from code. Your AI reads the repository where it already works and proposes the model: context, containers, components, ER diagrams from migrations. Keystone never receives your source code.
  • Gives the agent the part it needs. The agent asks for one module, what depends on an element, the path between two elements or only what changed since last time, instead of the whole model.
  • Keeps the model current. After code changes the AI checks the diagram against the code and sends a proposal, by hand or from CI: the AI assistant generates the job for GitHub Actions or GitLab CI.
  • You stay the reviewer. Every AI proposal arrives as a branch: open it, correct it, merge it or reject it. Merges are three-way, field by field.
  • More than boxes. Scenarios, architecture decisions (ADR) bound to elements, impact analysis, antipattern review with remediation plans, comments, live co-editing, roles and access, system design interview practice.
  • No lock-in. Export to PNG, SVG, Markdown with Mermaid, Structurizr DSL and Obsidian notes; import a Structurizr workspace (JSON or DSL).

On a question about one module, the module slice took 68–77% fewer input tokens than sending the whole model, with the same facts in the answer. This compares a slice with the whole model, not a whole coding task (method and limits).

Claude Code plugin

Install Keystone as a plugin; Claude Code asks for your token once and keeps it in secure storage:

/plugin install keystone-architecture --marketplace runafterasun/keystone-core

Connect your AI

  1. Sign in at https://keystone-core.pro and open a project → AI assistant → Connection → Create token.
  2. Add the MCP server in the folder with the code of that project, or install the plugin above.

Claude Code

bash
claude mcp add --scope local --transport http keystone https://keystone-core.pro/mcp --header "Authorization: Bearer ks_…"

Cursor (.cursor/mcp.json)

json
{ "mcpServers": { "keystone": { "url": "https://keystone-core.pro/mcp", "headers": { "Authorization": "Bearer ks_…" } } } }

VS Code with GitHub Copilot (.vscode/mcp.json)

json
{ "servers": { "keystone": { "type": "http", "url": "https://keystone-core.pro/mcp", "headers": { "Authorization": "Bearer ks_…" } } } }

Gemini CLI (.gemini/settings.json)

json
{ "mcpServers": { "keystone": { "httpUrl": "https://keystone-core.pro/mcp", "headers": { "Authorization": "Bearer ks_…" } } } }

Windsurf (~/.codeium/windsurf/mcp_config.json)

json
{ "mcpServers": { "keystone": { "serverUrl": "https://keystone-core.pro/mcp", "headers": { "Authorization": "Bearer ks_…" } } } }

Clients with local (stdio) servers only, through the mcp-remote bridge (needs Node.js):

json
{ "mcpServers": { "keystone": { "command": "npx", "args": ["-y", "mcp-remote", "https://keystone-core.pro/mcp", "--header", "Authorization:${AUTH_HEADER}"], "env": { "AUTH_HEADER": "Bearer ks_…" } } } }

A token follows the current role of its owner in the project: a viewer's token only reads. More in the guide.

Prompts

Ready commands the server offers to your client, for example in Claude Code /mcp__keystone__build_architecture <project link>:

PromptWhat it does
build_architectureContext and containers from the code
build_architecture__fullThe whole architecture: also components and tables
describe_containerBreak a container into components with their public API
describe_databaseDraw the ER diagram of a database from its migrations
describe_scenarioTrace a scenario through the architecture
record_decision, import_decisionsRecord an architecture decision, import existing ADRs
validate_architectureCheck the diagram against the code
syncBring the diagram up to date with the commits since the last sync
analyze_impactWhat a change of an element affects, with paths and reasons
review_antipatterns, plan_remediationFind architecture antipatterns, plan their fixes in stages
system_design_interviewPractise a system design interview on a real diagram

Tools

Reading tools return the part of the model a task needs:

ToolWhat it returns
search_architectureElements and tables by name, role or module, with IDs and ready reads for the hits
get_architectureThe whole model as a short map, one module or chosen elements in full
traverse_architectureWhat depends on an element and what it depends on, to a chosen depth
analyze_impactWhat a change of an element or table affects, with reasons and paths
find_architecture_pathThe chain of calls and data access between two elements
get_architecture_deltaOnly what changed since a version of the model
find_antipattern_candidatesShared databases, cycles of synchronous calls, overloaded services

Changes go through propose_changes only: a proposal becomes a branch that a person reviews and merges. Checks against the code and antipattern findings are reported with report_validation and report_antipatterns.

Plans and hosting

  • keystone-core.pro has a free plan with limits.
  • Self-hosted inside your own network for companies: contact us.

Feedback

Questions, ideas and bug reports are welcome as issues.

來源:README.md,提交 5a406f2

工具

0
該伺服器需要 API 金鑰等憑證,因此 SourceWeft 無法在沒有憑證的情況下讀取其工具,也未收錄。

版本歷史

1
  1. v1.0.0最新Nov 11, 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。