Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
UMTRI_API_TOKEN, UMTRI_API_BASE标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.umtri.io打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"umtri": {
"command": "npx",
"args": [
"-y",
"umtri-mcp"
],
"env": {
"UMTRI_API_TOKEN": "your-value",
"UMTRI_API_BASE": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http umtri https://mcp.umtri.ioclaude mcp add umtri --env UMTRI_API_TOKEN=your-value --env UMTRI_API_BASE=your-value -- npx -y umtri-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"umtri": {
"url": "https://mcp.umtri.io"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"umtri": {
"command": "npx",
"args": [
"-y",
"umtri-mcp"
],
"env": {
"UMTRI_API_TOKEN": "your-value",
"UMTRI_API_BASE": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"umtri": {
"type": "http",
"url": "https://mcp.umtri.io"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"umtri": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"umtri-mcp"
],
"env": {
"UMTRI_API_TOKEN": "your-value",
"UMTRI_API_BASE": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://mcp.umtri.io菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
UMTRI_API_BASE env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
服务器要求先登录,才会列出它的工具。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 umtri.io 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 199 毫秒内响应(HTTP 401)
需要你自己复制粘贴密钥或令牌
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:UMTRI_API_TOKEN
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(1.7.1)于今天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, LickityClick
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Create, edit and track LickityClick short links, campaigns and click stats from your AI assistant.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
MCP server for Umtri — give your AI coding agent a persistent map of your project's structure, dependencies, and bugs.
Your agent re-derives your codebase from scratch every session. Umtri stores the structure once and hands it back through MCP: a tree of what the system is made of, the calls and dependencies between its parts, and the bugs eroding it. Ask "what breaks if I change this?" and get an answer traced through recorded connections rather than guessed from a grep.
The fastest path is the hosted endpoint at https://mcp.umtri.io — nothing to install. Generate a token at app.umtri.io → Settings → API Tokens, then:
claude mcp add --transport http umtri https://mcp.umtri.io \
--header "Authorization: Bearer umtri_pat_xxxxxxxxxxxxxxxx"
Any MCP client that takes a config object uses the same shape:
{
"mcpServers": { "umtri": { "type": "http", "url": "https://mcp.umtri.io", "headers": { "Authorization": "Bearer umtri_pat_xxxxxxxxxxxxxxxx" } } } }
Use this package when you want to pin a version or point at a self-hosted API:
claude mcp add umtri \
-e UMTRI_API_TOKEN=umtri_pat_xxxxxxxxxxxxxxxx \ --transport stdio \ -- npx -y umtri-mcp
| Variable | Required | Default |
|---|---|---|
UMTRI_API_TOKEN | yes | — |
UMTRI_API_BASE | no | https://api.umtri.io |
The token is not validated at setup time, so a bad token connects but every call fails. If tools appear and then error, re-check the token and its scope — read tokens cannot call any write tool.
Read — get_graph, get_bug, get_impact, list_projects, list_bugs, list_seasons, list_events, export_ground
Write — create_project, create_node, update_node, delete_node (a subtree only with cascade: true), create_edge, delete_edge, create_api, update_api, delete_api, create_bug, update_bug, delete_bug, create_season (acts only after the user confirms)
Plan loop — commit_plan, record_commit
Wiki — list_wiki, get_wiki, list_wiki_revisions, write_wiki, edit_wiki, delete_wiki. The ground's encyclopedia: pages form a table of contents (parent, position) read from an overview down, each has a kind, and every write comes back with warnings when a page strays from the skeleton.
Feedback — send_feedback files a suggestion or defect about Umtri itself.
get_graph returns a slice, not a dump: scope by subtree (rootId), by layer (maxType), by role, or by season, and control description weight separately. A large tree stays cheap to read.
Ten read-only documents the agent can pull for domain rules — the plant vocabulary (trunk/limb/twig/leaf/vein), what counts as a node and what does not, how seasons work, how plan nodes are meant to be realized, how a ground behaves while transplanting, keeping the tree in step with commits, and how to write and organize the wiki.
umtri://rules/vocabulary umtri://rules/plan
umtri://rules/vocabulary-detailed umtri://rules/commit-sync umtri://rules/system-structure umtri://rules/wiki umtri://rules/seasons umtri://templates/wiki umtri://rules/transplant umtri://about/vision
Apache-2.0. See LICENSE.