SEO Content Machine

com.seocontentmachine由 seocontentmachine.com 发布v1.1.1更新于 Nov 3, 2026

Run SEO Content Machine tasks from an MCP client: scraping, crawls, Google Maps, Workspace pages.

已验证STDIO仅桌面效率与工作流网页搜索与抓取

概览

SEO Content Machine 的本地 MCP 服务，由 seocontentmachine.com 发布；无需登录；STDIO。

暂无 AI 概览：以下信息来自注册中心条目和服务本身。

发布者
seocontentmachine.com

安装

在 SourceWeft 中

  1. 打开 控制台中的 SEO Content Machine，将其添加到工作区。
  2. 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

SEO Content Machine MCP server

Connects Claude Code, Codex, Claude Desktop or any MCP client to SEO Content Machine (SCM), the desktop SEO workspace.

Your assistant can then create and run SCM tasks and read their results: article scraping from search results, site crawls, search result lists, Google Maps listings, YouTube subtitles, archive.org downloads and SEO Workspace pages. The work runs inside the SCM app on your machine, with its own browser and task queue.

Requirements

  • SEO Content Machine running on the same machine, on Windows, Mac or Linux. There is a 14-day free trial, no card needed.
  • Node.js 18 or newer.

Setup

Claude Code:

claude mcp add scm -- npx -y seo-content-machine-mcp

Any other MCP client, in its config file:

json
{  "mcpServers": {    "scm": {      "command": "npx",      "args": ["-y", "seo-content-machine-mcp"]    }  }}

If you set an API key in SCM (Settings > App > Api secret key), pass it as SCM_API_KEY. If SCM's API runs somewhere other than http://localhost:8008, set SCM_API_URL.

Tools

ToolWhat it does
task_list, task_get, task_resultsList SCM tasks, read one with its log, read the result rows of its last run, which point to its output files
task_run, task_cancel, task_deleteStart (or start over with fromStart), stop or delete a task
page_pipeline_upsertCreate or change a Page Pipeline: AI pages from page templates, or articles scraped from search results, for a list of keywords
dynamic_pages_createExtract values from rendered pages into CSV with CSS selectors
static_pages_createFetch pages without a browser and save each as a cleaned article
site_crawler_createCrawl a site and save the links it finds
url_finder_createSearch a list of queries and save every result to one CSV of query, rank, url and title
youtube_subtitles_createSave the subtitles of YouTube videos, from video URLs or keyword searches
web_archives_createDownload the newest archive.org copy of each page on a domain
local_listings_createScrape Google Maps listings, such as "plumbers in denver"
seo_workspace_createCreate an empty SEO Workspace
workspace_queryRead an SEO Workspace: its pages, site plan, brief, documents, crawl and Search Console data
workspace_writeAdd or update pages, the site plan, the brief or documents in an SEO Workspace, with undo in the app
workspace_create_pagesHand SEO Workspace pages to a Page Pipeline, which researches, writes and reviews each one as a draft
workspace_documents_editReplace exact text in one SEO Workspace document
web_search, browser_open, cdp_openSearch the web, read a page, or drive a real browser
render_pdfPrint an HTML document to a PDF file

How it works

SCM serves MCP over HTTP at /mcp inside the app. This package is a small stdio relay: the client talks to it over stdin and stdout, and it forwards each message to the app. You can start SCM before or after your MCP client. While SCM is closed the server lists no tools, and it tells the client to list them again once SCM starts. Tool calls made while SCM is closed return an error that says to start it.

来源：mcp/README.md，提交 8c2123a

工具

0
SourceWeft 已读取该服务器，它没有列出任何工具。

版本历史

2
  1. v1.1.1最新Nov 3, 2026
  2. v1.1.0Sep 30, 2026

评分

已满足适用检查项的 75%

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
  • 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。

  • 已列出工具必需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