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)
Agent-first bookmark management with auto-registration, categories, tags, and shared collections.
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。
FOOTPRINTS_ENDPOINT, FOOTPRINTS_TOKEN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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"url-manager": {
"command": "uvx",
"args": [
"url-manager-mcp"
],
"env": {
"FOOTPRINTS_ENDPOINT": "your-value",
"FOOTPRINTS_TOKEN": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add url-manager --env FOOTPRINTS_ENDPOINT=your-value --env FOOTPRINTS_TOKEN=your-value -- uvx url-manager-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": {
"url-manager": {
"command": "uvx",
"args": [
"url-manager-mcp"
],
"env": {
"FOOTPRINTS_ENDPOINT": "your-value",
"FOOTPRINTS_TOKEN": "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": {
"url-manager": {
"type": "stdio",
"command": "uvx",
"args": [
"url-manager-mcp"
],
"env": {
"FOOTPRINTS_ENDPOINT": "your-value",
"FOOTPRINTS_TOKEN": "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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
FOOTPRINTS_ENDPOINT 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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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8日
注册名称已通过 GitHub 账户 Piccolo123 验证,该账户拥有此仓库
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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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 1 项适用的基础检查中通过了 1 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:FOOTPRINTS_TOKEN
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.0.2)于3个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, SolveHub
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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.
CAPTCHA and anti-bot solving for Turnstile, DataDome, Akamai, PerimeterX and Imperva.
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。
English | 简体中文
Deliver results as beautiful cards, not raw link dumps. A Model Context Protocol server for saving, organizing, searching, and sharing web resources — cross-device sync, categories, tags, full-text search, batch operations, and team sharing. 21 tools with auto-registration so no manual setup is required.
📖 Usage patterns and best practices → [URL Manager Skill](https://github.com/Piccolo123/url-manager/blob/main/SKILL.md)
The content human users want to save is everywhere — a YouTube workout video, an Amazon gear link, a Substack training plan — scattered across platforms with no connection.
URL Manager fixes this. Paste any link from any platform. AI auto-identifies the content and suggests a category — confirm and it's a footprint. All saves flow into one platform-agnostic library, organized and always findable. Then share in one click — hand your curated knowledge base to your team, and everyone stays in sync.
A structured, searchable record — a web link, a plain-text note, an idea, or anything worth saving.
| Field | Type | Description |
|---|---|---|
id | UUID | Permanent unique identifier — use for all operations |
url | string (8192) | Original link. Can be empty for text-only footprints |
title | string (512) | Short title |
description | string (1024) | Additional context or notes |
content_type | string (50) | Free text (e.g. article, video, image). Use list_content_types() to see existing values |
category_ids | list[int] | Which categories this belongs to — you assign |
tag_names | list[str] | Free-form keywords — you assign |
A footprint can belong to multiple categories simultaneously.
Like a folder, but a footprint can be in several at once.
| Field | Type | Description | |
|---|---|---|---|
id | int | Permanent numeric identifier — always reference by ID | |
name | string (50) | Display name | |
mode | string \ | null | null = personal, "cocreate" = shared co-edit, "subscribe" = shared read-only |
A container that groups related categories. Every user starts with "My Categories" (personal) and "Shared Categories" (shared container).
Category Sets (workspaces)
└── Categories (labels like "Shopping", "Learning") └── Footprints └── Tags (free-form keywords)
| Personal | Shared | |
|---|---|---|
mode | null | "cocreate" or "subscribe" |
| Visible to | Only you | You + invited members |
| Members & invite links | No | Yes |
Cocreate — everyone adds/removes footprints. Subscribe — read-only for members (writing returns 403).
| Action | Owner | Admin | Member |
|---|---|---|---|
| Add/remove footprints (cocreate) | ✅ | ✅ | ✅ |
| Add/remove footprints (subscribe) | ✅ | ❌ | ❌ |
| Generate invite link (cocreate) | ✅ | ✅ | ✅ |
| Generate invite link (subscribe) | ✅ | ❌ | ❌ |
| Switch cocreate ↔ subscribe | ✅ | ❌ | ❌ |
| Manage members | Web UI only | — | — |
query _(required)_ — Search keywordslimit — Results per page (default 10, max 100)offset — Pagination offset (default 0)category_id=0 returns all.limit — Results per page (default 20, max 100)offset — Pagination offset (default 0)footprint_id _(required)_ — From list_footprints or search_footprints results (field id)list_categories() and list_tags() first to discover existing structure.url _(required)_ — Web page URLtitle — Leave empty to auto-extract from the pagedescription — Summary or notescategory_ids — Comma-separated IDs, e.g. "1,3"tag_names — Comma-separated names, e.g. "AI,tutorial"category_ids replaces the entire list — not append. Call get_footprint() first, then merge IDs.footprint_id _(required)_ — From search or list resultsid, name, and mode fields. mode=null → personal; mode="cocreate"/"subscribe" → shared.list_categories() first to avoid duplicates.name _(required)_ — Category namecategory_set_id — Parent category set (0 = default)name _(required)_ — Category set namename _(required)_mode _(required)_ — "cocreate" (multiple editors) or "subscribe" (read-only)description — Optional description ⚠️ In subscribe mode, adding bookmarks returns 403. Use "cocreate" for editable collaboration.shared_category_id _(required)_ — From list_categories() (shared entries)duration_hours — Default 24invite_code _(required)_ — 8-character code from the invite linkupdates _(required)_ — JSON string: [{"id":"...", "title":"New Title", "category_ids":"1,3"}, ...] Each object may contain title, description, category_ids, tag_names; id is required.1. agent_register() → get token (auto-memorized)
1. my_info() → confirm identity
1. create_shared_category(name="Team KB", mode="cocreate")
# ❌ Wrong: moving bookmark 42 to category 7 loses existing categories 3 and 5
update_footprint(42, category_ids="7")
get_footprint(42) → existing categories [3, 5] update_footprint(42, category_ids="3,5,7")
Writing to a subscribe-mode shared category returns 403. If the user says "I subscribed but can't add anything", explain it's read-only — the creator needs to change it to cocreate.
Each call creates a fresh empty account. Always check for a saved token first. If unsure, call my_info() to verify the current token is valid.
Rapid consecutive calls may trigger HTTP 429. Add short delays between batch operations; on 429, wait a few seconds and retry.
Inviting or removing members from shared categories requires the web UI at https://ai.ocean94.com. You cannot do this programmatically.
search_footprints for targeted queries instead of dumping everythinglist_categories() and list_tags() before adding to avoid duplicatesURL Manager excels at saving and organizing. Pair it with tools that excel at discovering and fetching:
Fetch MCP scrapes web → add_footprint() → auto-categorized, permanent, searchable
Firecrawl crawls pages → add_footprint() → organized into cards Brave Search finds URLs → add_footprint() → one-click save from search results
Agents just pass the upstream MCP's URL + title as params to add_footprint.
git clone https://github.com/Piccolo123/url-manager-mcp.git
cd url-manager-mcp pip install -r requirements.txt
Or from PyPI:
uvx url-manager-mcp # or: pip install url-manager-mcp
https://ai.ocean94.comAdd to your profile's cordis.patch.yml (e.g. ~/.dsh/profiles/headless/cordis.patch.yml or the web profile):
- insert:
All 21 tools appear as mcp__url_manager__* (add_footprint, search_footprints, list_categories, agent_magic_link, …). The model auto-registers on first use — no API key needed.
只显示了开头部分;其余内容请在仓库中阅读