veddata MCP server
io.github.SanZiNEO/veddata·v0.2.0·2 starsMCP server for AI agents: discover a web page's data sources and drive the page to reach them.
2 stars127 downloads/wk
Reviews
Write oneNobody has reviewed veddata yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
veddata tools (30, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
ved_actved_apis列出已捕获的所有数据。包括网络请求、DOM 内嵌数据、JS 变量等。每条记录标注触发时机,不贴类型标签。
ved_chain工具链:一次把多个工具按顺序交给服务端连续执行。
ved_closeClose the browser and clear all captured data.
ved_console操作页面控制台:执行 JS / 查看 log/warn/error 消息。
ved_contextSearch all data sources for keyword, returning field paths and values.
ved_cookiesView cookies for the current page.
ved_dom_locate通过路径定位一个 DOM 节点。
ved_dom_search在内存 DOM 树中搜索文本。
ved_dom_tree输出当前页面的 DOM 目录树(内存快照,含容器/字段/交互标记)。
ved_export导出捕获到的 API 数据源(一个或多个)。
ved_export_all一次导出当前 tab 捕获到的所有 API 数据源。
ved_fetch获取页面全文,辅助定位数据关键词。当需要从页面文本中选取关键词来反查数据时使用。
ved_goto导航到目标页面,自动发现所有数据来源。返回 DOM 结构、网络请求、内嵌数据清单。
ved_inspectShow full request and response details for one or more APIs.
ved_list_scripts列出页面所有 JS 脚本的 URL、大小和行数。
ved_open启动数据发现会话。打开浏览器以开始捕获页面数据源。浏览网页是前置步骤,不是终点。
ved_peek快速探测指定 URL 的数据源。打开页面 → 自动捕获 API → 返回字段文档。
ved_requestwrite actionSend a test HTTP request — replay from captured API or fully custom.
ved_scanComprehensive page data source scanner.
ved_screenshot截图当前页面。
ved_script_source局部查看:查看某个脚本源码,支持搜索高亮和上下文。
ved_search在已捕获的所有数据中搜索关键词。包括网络请求、DOM 内嵌 JSON、页面渲染文本和 JS 全局变量。
ved_search_scripts全局搜索:在所有已加载的 JS 源码中搜索字符串。
ved_status状态体检:现在有哪些标签页、各自在哪个页面、有没有撞上人机门。
ved_tab_closeClose browser tab(s) by CDP short ID and prune their API records.
ved_tab_switchSwitch the active tab by CDP short ID (from ved_tabs output).
ved_tabsList all open browser tabs with their URLs — 这是"重新建档"的入口。
ved_trace_value全局搜索一个值出现在哪些地方。
ved_watch批量观测:注册请求/JS 观测点 → 触发操作 → 一次性取回快照。
Public scan report
scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it
- Code scan27 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 3 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How veddata compares
Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 1,299 Productivity servers
- Tools
- 30
- the typical Productivity server has 7
- Tools that change things
- 3%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 2
- more than 60% of 854 Productivity servers
- Downloads a week
- 127
- more than 62% of 427 Productivity servers with a package
What its tools let an agent do: 29 read · 1 change
Release history: 2 versions in the registry since 2026-09-10, latest 2026-10-11, typically one every 31 days.
Install veddata in Claude Code, Cursor or VS Code
claude mcp add veddata -- uvx veddata
What the publisher says
From the veddata repository's README, as published. We do not edit it. Read it on GitHub
斥候(veddata)
<!-- mcp-name: io.github.SanZiNEO/veddata -->
一个模型上下文协议(MCP)服务器:在网页上做数据源发现 —— 捕获网络请求、提取内嵌数据、分析脚本,并通过交互与监测点跟踪数据流向。
English
功能
- 网络数据源:页面发出的全部请求与响应,按接口归并并给出字段结构
- 内嵌数据: 标签里的 JSON 与 window 全局变量
- 脚本分析:列出与搜索已加载脚本、读取源码、追踪一个值出现在哪些位置
- 交互:点击、输入、选择、滚动,按可见文本或 css=、//(XPath)选择器定位
- 监测点:请求监测(匹配到指定模式即记录)与 JS 断点监测(命中时抓取作用域变量快照)
- 文档结构:DOM 树快照、关键词定位、按路径定位,全部在服务端内存中完成
- 工具链:一次调用顺序执行多个工具(支持等待与重复),并为每个动作给出因果差分
- 页面事实:地址、标题、正文长度、关键词命中的原文片段、可见与隐藏的组件
- 下载:发生下载时在消息中给出文件名、保存路径、状态与大小
- 服务端留存:结果留在服务端,返回压缩摘要,明细随时按需获取
环境要求
- Python 3.10 及以上
- Chrome 或 Edge(默认以有窗口模式启动,并使用持久化配置目录保留登录状态)
安装与使用
一次性运行(无需安装,推荐):
{
"mcpServers": {
"veddata": {
"command": "uvx",
"args": ["veddata", "--response-dir", "E:\\path\\to\\out"]
}
}
}或先安装再使用:uv tool install veddata(或 pip install veddata),然后
{
"mcpServers": {
"veddata": {
"command": "veddata",
"args": ["--response-dir", "E:\\path\\to\\out"]
}
}
}从源码运行(开发用):
uv venv
uv pip install -e ".[dev]"客户端配置(标准输入输出):
{
"mcpServers": {
"veddata": {
"command": "E:\\path\\to\\veddata\\.venv\\Scripts\\python.exe",
"args": ["-m", "veddata.server",
"--profile-dir", "E:\\path\\to\\profile",
"--response-dir", "E:\\path\\to\\out"]
}
}
}配置项
工具
会话与标签页
- vedopen** — 启动会话(自行启动一个普通 Chrome 并通过调试协议接管)
- vedstatus** — 当前页面事实、标签页清单、已捕获条数、状态账本
- vedtabs、vedtabswitch、vedtabclose** — 标签页清单、切换、关闭
- vedclose** — 关闭浏览器并清空捕获数据
导航与读取
- vedgoto** — 导航,返回文档结构、数据源预览与页面事实
- vedfetch** — 取当前页正文(分页)
- veddomtree、veddomsearch、veddomlocate — 树快照、关键词、路径
- vedconsole** — 执行 JS 或读取控制台消息
- vedcookies、vedscreenshot — cookie 与截图落盘
交互
- vedact** — input、click、select、scroll;可单步或链式;target 支持可见文本、css= 或 //
数据源
- vedapis、vedinspect — 捕获清单与单条详情(请求头、响应体、字段结构)
- vedexport、vedexportall** — 导出到磁盘(原始或精简)
- vedpeek** — 打开网址并直接返回数据源清单
- vedrequest** — 重放已捕获的接口或发送自定义请求(自动带上 cookie)
- vedsearch、vedcontext、vedtracevalue — 跨网络、内嵌、脚本、全局变量的搜索与追踪
脚本
- vedlistscripts、vedsearchscripts、vedscriptsource — 清单、搜索、源码
监测点
- vedwatch** — 注册、列表、收集、删除;分为请求与 JS 两类;命中快照留在服务端
扫描
- vedscan** — 一次性汇总网络、文档结构与内嵌数据
工具链
- vedchain** — 顺序执行多个工具;等待支持毫秒、网络命中、网络静默、元素可见性;重复块支持一层
行为说明
- 只陈述事实:输出说明有什么,不含判断与下一步提示;页面状态以地址、标题、正文长度、关键词命中片段、可见组件等事实呈现。
- 结果留在服务端:返回压缩摘要与分页页脚,明细用 vedapis、vedinspect、ved_watch(collect) 等按需获取。
- 状态观测:发生在工具之外的变化(页面自行跳转、标签页增删)之后,依赖活状态的工具会返回一条事实说明而不执行;vedstatus、vedtabs 会重新建立观测。
- 人机协作:界面可见,登录或验证由用户在窗口中完成;工具照实报告当前页面事实。
- 浏览器生命周期:自行启动的浏览器由 vedclose 关闭;通过 BROWSERADDRESS 接管的仅断开连接。
示例:没有接口文档的站点,怎么拿到下载直链
以 svgrepo 为例(该站点没有公开接口文档,AI 只能自己侦察)。一条工具链跑完:
[
{"tool": "ved_open"},
{"tool": "ved_goto", "args": {"url": "https://www.svgrepo.com/vectors/arrow/"}},
{"tool": "ved_goto", "args": {"url": "https://www.svgrepo.com/svg/535197/arrow-u-up-left"}},
{"tool": "ved_act", "args": {"action": "click", "target": "css=a[href*='/download/']"}}
]消息里直接给出事实(动作、因果、落盘位置):
[click] Clicked 'css=a[href*='/download/']' → +1 new APIs
GET https://www.svgrepo.com/_next/data/XJiZPe18H5paekHV…/tools.json
download: arrow-u-up-left-svgrepo-com.svg → E:\Downloads\arrow-u-up-left-svgrepo-com.svg (completed, 399 B)开发
pytest tests -q
python scripts/smoke.pyShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
veddata: common questions
- Is veddata MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the veddata safety report
- How do I install veddata?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does veddata need an API key?
- No secret keys are declared. It reads 2 settings from the environment.
- Is veddata maintained?
- The last commit was 24 days ago (2026-10-11). The latest release is v0.2.0.
- What can I use instead of veddata?
- Servers from other publishers that do the same job: Argent MCP server, Sceneview MCP server and SceneView MCP server.
- How does veddata compare with other Productivity MCP servers?
- safety score 89/100 (higher than 80% of 1,299 Productivity servers); tools 30 (the typical Productivity server has 7); tools that change things 3% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to veddata
Same job from other publishers: the closest match first, then the best rated.
- ArgentDrive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agentnot reviewedWidely usedA
- Sceneview3D & AR SDK for Android, iOS, Web — API docs, samples, validation, and code generation.not reviewedEstablishedA
- SceneView3D & AR SDK for Android, iOS, Web — API docs, samples, validation, and code generation.not reviewedEstablishedA
- gflow-cliDrive Google Flow from an agent: Veo video and Imagen image generationnot reviewedEstablishedA
- Buoy GgLet AI agents read and drive a running React Native or Flutter app through Buoy's devtools.not reviewedEstablishedA