mcpField
O
OpenSEO

OpenSEO

远程服务
openseo.so其他27.6k今天更新

关于 OpenSEO

OpenSEO 是面向用户和 AI Agent 的开源 SEO 工具,涵盖关键词研究、网站审计、排名跟踪、反向链接、竞品洞察和 AI 可见度。它支持托管使用或自托管,并通过 DataForSEO API 密钥获取 SEO 数据。

主要功能

  1. 01关键词研究与排名跟踪
  2. 02网站审计和反向链接工作流
  3. 03竞品洞察与 AI 可见度
  4. 04支持托管和自托管部署
  5. 05使用自有 DataForSEO API 密钥

适用场景

  1. 01研究关键词并跟踪排名
  2. 02审计网站并检查反向链接
  3. 03查看竞品 SEO 数据
  4. 04让 AI Agent 执行 SEO 工作流

MCP 相关

OpenSEO 提供 MCP 服务,让 AI Agent 和 MCP 客户端访问 SEO 数据与工作流。Agent Skills 提供通过 MCP 执行 SEO 任务的可复用指引。

配置

远程服务无需本地安装。选择你使用的客户端,复制配置或使用一键安装。

服务地址https://app.openseo.so/mcp
一键复制安装命令
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

命令在终端中运行;JSON 粘贴到对应客户端的 MCP 配置后重启。需要授权的服务会在首次连接时提示登录。

工具

README 原文English

来自项目 README

README 暂无中文译文,以下为英文原文;中文介绍见上方。

OpenSEO

Open source alternative to Semrush and Ahrefs

OpenSEO is an SEO tool for the people. If tools like Semrush or Ahrefs are too expensive or bloated, OpenSEO is a pay-as-you-go alternative that you actually control.

All-in-one SEO tool for you and your AI agent.

Connect with any agent like Claude Code, OpenClaw or Hermes. We have pre-built skills, but you can build your own to tailor OpenSEO to your needs.

openseo-keyword-research

Hosted Version

Try OpenSEO for free on our website. If you want to support the project, a hosted subscription is $10/month.

openseo.so

EveryApp

Host OpenSEO and other open source apps on our platform EveryApp.

Self-host on EveryApp and give it a star →

Why use OpenSEO?

  • Best in class MCP and AI Skills.
  • Modern, simple UI.
    • Focused workflows instead of a bloated, complex SEO suite.
  • No subscriptions.
    • Bring your own DataForSEO API key and pay only for what you use.
  • Fork and vibe code your own custom tool.

Main SEO Workflows

  • Keyword research
  • Rank tracking
  • Competitor Insights
  • Backlinks
  • Site Audits
  • AI Visibility

OpenSEO MCP & Agent Skills

OpenSEO exposes an MCP server so AI agents like Claude Code, OpenClaw, and Hermes can use your SEO data directly. Agent Skills are reusable workflows that guide your agent through SEO tasks using the MCP.

Self-Hosting

OpenSEO supports two self-hosting paths. Both use email and password accounts: the first visitor creates the admin account, teammates join from invitation links, and MCP clients (Claude, ChatGPT, Codex, Cursor) sign in with the same accounts.

  • Docker - On your own server or computer, with a prebuilt image that is ready in seconds. Works with Compose-based platforms such as Coolify, Portainer and Dokploy. See docs/SELF_HOSTING_DOCKER.md.
    • Running the older single-container image? It keeps getting updates; move to the new setup when you are ready, data included.
  • Cloudflare - No server to run: one deploy command puts OpenSEO on your own Cloudflare account (works on the free plan). See docs/SELF_HOSTING_CLOUDFLARE.md.

For security-conscious setups, two advanced options replace the accounts with your own network controls:

  • Cloudflare Access in front of the Cloudflare deploy, so Cloudflare checks every request before it reaches OpenSEO. See docs/SELF_HOSTING_CLOUDFLARE.md.
  • No sign-in on Docker, behind Tailscale, a private network or your own authenticating proxy. See Without sign-in.

Either way, you need a DataForSEO API key to get SEO data. See docs/DATAFORSEO_API_KEY.md.

Costs

OpenSEO needs a DataForSEO API key so that you can get SEO data. You pay them directly when self hosting.

See openseo.so/pricing

When you self host, your costs will be slightly lower than the estimates on our website. The way the hosted service makes money is by charging 28% extra for every request we make to DataForSEO.

Local Development

See docs/LOCAL_DEVELOPMENT.md.

Contributing

Creating clear issues is the best way to contribute.

Read more here: .github/CONTRIBUTING.md

We have this skill: /simple-issue-description which helps.

npx skills add every-app/open-seo --skill simple-issue-description

Community

Join Discord to chat: Discord

Follow along for updates:

评论

支持 Markdown

第一次接触 MCP?

从协议是什么,到在客户端里装上第一个服务,这几条回答覆盖了大多数入门问题。

一个开放协议,规定了 AI 应用如何以统一方式连接外部工具与数据源。客户端负责与模型对话,MCP 服务负责提供工具、资源和提示模板,两者通过标准消息通信,同一个服务可以被不同客户端复用。