
DOC Model Safety Gate
io.github.laceykes由 GitHub 账号 laceykes 发布v0.1.2更新于 Nov 20, 2026
AI agents propose content changes; a human reviews them; only reviewed work can publish.
概览
本地 MCP 服务器,将 AI 提议的内容变更暂存待人工审核,只有审核通过的运行才能发布。
- 可以做什么
- 列出并查看仍有待处理 AI 输出的审核运行,含字段、原值与 AI 值
- 接受、拒绝或编辑单条输出,或对一次运行中所有待处理输出批量接受/拒绝
- 在审核运行通过后正式发布工作流运行,并回滚已发布的运行
- 通过其他 Safety Gate API 工具检查工作流与图结构
- 适用场景
- 适用于 AI 代理在 CMS 或 Operations 层起草内容变更、且希望在上线前由人工决定的场景,且该限制由后端强制执行而非仅靠约定。
- 运行要求
- 通过 npx(Node.js)以 stdio 方式在本地运行,需要一个可访问的 Safety Gate GraphQL API 端点。必需环境变量:DOCMODEL_API_ENDPOINT、DOCMODEL_API_TOKEN 和 DOCMODEL_USER_ID;成员访问还需 DOCMODEL_PROJECT_ID,DOCMODEL_USER_ROLE 可选。本版本不包含托管端点。
安装
在 SourceWeft 中
- 打开 控制台中的 DOC Model Safety Gate,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
DOC Model Safety Gate
An AI can draft the change. It cannot publish it.
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.
The rule
- Propose — a workflow runs in dry-run mode. Nothing can publish from a dry run.
- Stage — AI outputs land in the Safety Gate with their original and proposed values, field by field.
- Review — a human accepts, rejects, or edits each output. Bulk review is available for whole runs.
- 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."
- Roll back — a published run can be rolled back when snapshots exist.
Tools
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.
Or from source:
Configuration
The older STRATA_* spellings of all five variables still work as fallback aliases.
Claude Desktop / Cursor
Claude Code
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.
来源:README.md,提交 18ad4a3
工具
0版本历史
1- v0.1.2最新Nov 20, 2026
评分
已满足适用检查项的 50%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分
其他 Model 集成

model.tools — Zero-Auth Agent Utilities
tools.model官方发布者
零认证远程工具服务器,为智能体提供一次性邮箱验证码读取、持久检查点、Webhook 收件箱、定时唤醒、任务回执与网页转 Markdown。
NLP.COM.AI Open Model Catalog
ai.com.nlp官方发布者
搜索精选的开放权重AI模型发布、许可证、架构和原始来源。AI 翻译

Hologram Model Hub
foundation.uor.hub官方发布者
一个远程 MCP 服务器,让助手搜索开放模型索引,并获取带 SHA-256 校验值的下载链接。

MCPShelf Model Context Protocol Registry, Search & Security Auditor
由 GitHub 账号 RitualDev-Lab 发布
本地 MCP 注册表浏览工具,让助手查找、比较 400 多个 MCP 服务器的信任评分并获取安装配置片段。

ModelPick
由 GitHub 账号 Leizhidong-creator 发布
本地 stdio MCP 服务器,为每个任务节点推荐应使用的 AI 模型,并给出每个已解决任务的成本与接入方式。