DOC Model Safety Gate

io.github.laceykes由 GitHub 帳號 laceykes 發布v0.1.2更新於 Nov 20, 2026

AI agents propose content changes; a human reviews them; only reviewed work can publish.

發布方自己的服務:model.tools — Zero-Auth Agent Utilities

已驗證STDIO僅桌面效率與工作流開發者工具

概覽

AI 產生的概覽

本機 MCP 伺服器,將 AI 提出的內容變更暫存待人工審核,只有審核通過的執行才能發布。

可以做什麼
  • 列出並檢視仍有待處理 AI 輸出的審核執行,含欄位、原值與 AI 值
  • 接受、拒絕或編輯單筆輸出,或對一次執行中所有待處理輸出批次接受/拒絕
  • 在審核執行通過後正式發布工作流程執行,並回滾已發布的執行
  • 透過其他 Safety Gate API 工具檢查工作流程與圖結構
適用情境
適用於 AI 代理在 CMS 或 Operations 層起草內容變更、且希望在上線前由人工決定的情境,且此限制由後端強制執行而非僅靠慣例。
執行需求
透過 npx(Node.js)以 stdio 方式在本機執行,需要一個可連線的 Safety Gate GraphQL API 端點。必要環境變數:DOCMODEL_API_ENDPOINT、DOCMODEL_API_TOKEN 與 DOCMODEL_USER_ID;成員存取另需 DOCMODEL_PROJECT_ID,DOCMODEL_USER_ROLE 為選用。此版本不含託管端點。
安裝前請注意
DOCMODEL_API_TOKEN 是送往所設定 API 端點的 Bearer 權杖,請僅指向可信任的端點。伺服器以 DOCMODEL_USER_ID 中的身分行事,可發布或回滾執行,批次審核會一次接受或拒絕多筆輸出。此伺服器仍在 1.0 之前的積極打包階段。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 DOC Model Safety Gate,將其新增到工作區。
  2. 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

DOC Model Safety Gate

An AI can draft the change. It cannot publish it.

[The Safety Gate loop: an agent proposes a change, the gate holds it, a human reviews it, and only then does it publish]

The DOC Model builds software in three layers — Data, Operations, Components. This MCP server enforces the DOC rule for AI agents working in the Operations layer: an agent can propose changes to your content, but every proposal is staged for human review, and only reviewed work can go live.

AI agents can write to your CMS the moment you connect them to it. This server puts a gate in between: everything an agent produces is staged for review, a human decides, and only reviewed work can go live. If an output is still pending, the publish call itself is refused — the gate is enforced by the backend, not by a warning label.

[How the Safety Gate works: AI agent, Safety Gate, human review, published site — plus undo and a record of every decision]

The rule

  1. Propose — a workflow runs in dry-run mode. Nothing can publish from a dry run.
  2. Stage — AI outputs land in the Safety Gate with their original and proposed values, field by field.
  3. Review — a human accepts, rejects, or edits each output. Bulk review is available for whole runs.
  4. Publish — a live run is only permitted once its review run has no pending or rejected outputs. Attempting to publish early returns an error: "Node … has pending AI output. Review all outputs before LIVE run."
  5. Roll back — a published run can be rolled back when snapshots exist.

Tools

ToolWhat it does
listPendingReviewsList gate runs that still have outputs waiting for a decision.
getGateReviewRead one gate run's outputs: field, original value, AI value, status.
reviewOutputAccept, reject, or edit a single output.
bulkReviewOutputsAccept or reject every pending output in a run at once.
publishReviewedRunRun a workflow live, gated on its review run. The review run ID is required — there is no way to call this "around" the gate.
rollbackRunRoll a published workflow run back.

The server also includes workflow inspection and graph tools for the Safety Gate API; the gate tools above are the supported launch surface (see Status).

Quickstart

The server is a stdio MCP server that talks to a Safety Gate GraphQL API endpoint.

bash
npx doc-model-safety-gate

Or from source:

bash
npm installnpm run buildnode dist/index.js

Configuration

Environment variableRequiredPurpose
DOCMODEL_API_ENDPOINTyesGraphQL endpoint of the Safety Gate API, e.g. http://localhost:4001/graphql
DOCMODEL_API_TOKENyesBearer token sent to the API
DOCMODEL_USER_IDyesIdentity the server acts as (sent as the x-user-id header)
DOCMODEL_PROJECT_IDfor member accessProject the server is scoped to (x-project-id)
DOCMODEL_USER_ROLEnomember (default) or admin

The older STRATA_* spellings of all five variables still work as fallback aliases.

Claude Desktop / Cursor

json
{  "mcpServers": {    "doc-model-safety-gate": {      "command": "npx",      "args": ["-y", "doc-model-safety-gate"],      "env": {        "DOCMODEL_API_ENDPOINT": "http://localhost:4001/graphql",        "DOCMODEL_API_TOKEN": "your-token",        "DOCMODEL_USER_ID": "your-user-id",        "DOCMODEL_PROJECT_ID": "your-project-id",        "DOCMODEL_USER_ROLE": "member"      }    }  }}

Claude Code

bash
claude mcp add doc-model-safety-gate \  -e DOCMODEL_API_ENDPOINT=http://localhost:4001/graphql \  -e DOCMODEL_API_TOKEN=your-token \  -e DOCMODEL_USER_ID=your-user-id \  -e DOCMODEL_PROJECT_ID=your-project-id \  -- npx -y doc-model-safety-gate

See it work

The loop at the top of this page is the real behavior, captured from a working local demo: an AI summary is proposed, staged in the Gate, and a publish attempted before review is refused by the backend; after the reviewer accepts, the identical call succeeds. The full build story — including the blocked publish, caught live — is told at thedocmodel.com.

The demo environment (Postgres + PostgREST + a mock CMS + the Safety Gate API) is not part of this repository; the server requires a Safety Gate API endpoint (see Status).

Status

Pre-1.0 and under active packaging. Verified end-to-end against a local Safety Gate API on 2026-11-12: pending reviews list and open correctly, human review flips output status, unreviewed publishes are refused by the backend, and reviewed publishes execute. The server requires a Safety Gate API endpoint; a hosted endpoint is not part of this release.

License

MIT — see LICENSE. Use it, build on it, ship it commercially if you like; the hosted layer and the DOC Model name stay ours.


Built by Lacey Kesler. The DOC Model Safety Gate is the enforcement layer of the DOC Model (Data · Operations · Components) — taught at thedocmodel.com: AI proposes, humans decide, and the audit trail shows both.

來源:README.md,提交 18ad4a3

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.1.2最新Nov 20, 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

其他 Model 整合