npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

seo-mcp-server

v3.0.5

Published

SEO MCP Server (minimal) - ai_content_detect only

Readme

SEO-MCP 文档(V3.0.0)——仅保留 ai_content_detect

本版本目标:精简为单一工具 ai_content_detect,用于在内容生成后、SEO质检前进行AI痕迹检测。其他工具(标题生成/内容指导/质检/模板版本管理)已移除对外暴露。

一、工具概述

  • 名称:ai_content_detect
  • 描述:AI内容生成检测:在内容生成后、SEO质检前进行AI痕迹检测,返回 percent、linesscore、mintxt,并给出 pass/review/fail 与下一步动作建议
  • 依赖环境变量:SEO_MCP_AI_DETECT_API_KEY(5118接口密钥)

二、安装与运行

推荐使用 npx 直接运行指定版本:

"seo-mcp": {
  "timeout": 60,
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "[email protected]"],
  "env": {
    "SEO_MCP_AI_DETECT_API_KEY": "YOUR_5118_API_KEY"
  }
}

或本地依赖:

npm install --save-dev [email protected]
"seo-mcp": {
  "timeout": 60,
  "type": "stdio",
  "command": "node",
  "args": ["./node_modules/seo-mcp-server/dist/index.js"],
  "env": {
    "SEO_MCP_AI_DETECT_API_KEY": "YOUR_5118_API_KEY"
  }
}

三、ListTools 与 CallTool

- ListTools 仅返回 ai_content_detect
- CallTool 仅支持 name=ai_content_detect,参数:
  - content: string(必填,建议≥100字)
  - locale?: string(默认 zh-CN)
  - thresholds?: { maxPercent?: number; reviewPercent?: number; minLineScore?: number }
- 返回字段:
  - percent: number;mintxt: 0|1;linesscore: {idx,score,txt}[]
  - decision: "pass"|"review"|"fail"; pass: boolean
  - next_actions: string[]; suggestions: string[]
  - diagnostics: { parser: "strict"|"relaxed"; raw: string; notes: string[] }

四、判定规则(默认阈值)

  • maxPercent(默认35):percent ≤ 35 → pass
  • reviewPercent(默认55):35 < percent ≤ 55 → review
  • minLineScore(默认3):任一段 score < 3 → 至少 review
  • mintxt != 0 → fail(长度不足)
  • errcode != "0" → fail(接口错误)

详细Schema与示例见 V2.1-schema.md。

五、示例调用(MCP CallTool)

请求:

{
  "name": "ai_content_detect",
  "arguments": {
    "content": "待检测文本……",
    "locale": "zh-CN",
    "thresholds": { "maxPercent": 35, "reviewPercent": 55, "minLineScore": 3 }
  }
}

返回(示例):

{
  "percent": 43,
  "mintxt": 0,
  "linesscore": [{ "idx": 1, "score": 3, "txt": "..." }],
  "decision": "review",
  "pass": false,
  "next_actions": ["remove_template_phrases", "add_verifiable_details"],
  "suggestions": ["存在边界风险段落,请按建议最小改写后复验"],
  "diagnostics": { "parser": "relaxed", "raw": "...", "notes": ["relaxed parse applied"] }
}

六、版本与回滚

  • 3.0.0 为“仅 ai_content_detect”精简版本;若需恢复完整生成/质检能力,请回滚到 2.2.1。
  • 回滚方式:将依赖版本切换为 [email protected],并恢复原配置。

七、FAQ

  • Q:为什么只剩一个工具?
    • A:满足“生成后、质检前”的AI痕迹硬性前置检查需求,减少配置与维护复杂度。
  • Q:是否仍需要配置模板?
    • A:无需。本版不再依赖模板系统的对外能力。
  • Q:API Key 如何配置?
    • A:通过环境变量 SEO_MCP_AI_DETECT_API_KEY 注入。

八、FAQ

  • Q:老项目未适配 next_action 会受影响吗?
    • A:不会。next_action 可忽略;原有字段不变。
  • Q:fix_instructions 一定要实现自动修复吗?
    • A:不要求;可展示给人工编辑使用。
  • Q:为什么不新增业务专用MCP?
    • A:为保持通用性与简洁性,业务差异放在调用侧(System Prompt/编排),MCP仅提供通用能力与最小辅助信息。

九、MCP宿主配置(推荐)

为确保宿主环境(如CodeBuddy)能稳定加载指定版本的seo-mcp-server,避免因全局安装的老旧版本或PATH环境问题导致加载失败(如Connection closed错误),推荐以下两种配置方式:

方案A:使用npx强制加载指定版本(推荐)

此方法无需本地安装,npx会自动下载并运行指定版本的包,是解决版本冲突和环境问题的最快方式。

配置示例:

"seo-mcp": {
  "timeout": 60,
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "[email protected]"],
  "env": {
    "SEO_MCP_AI_DETECT_API_KEY": "YOUR_5118_API_KEY"
  }
}

注意args中的版本号(@2.2.1)应与您需要使用的版本保持一致。

方案B:使用项目本地依赖(更稳定)

此方法将seo-mcp-server作为项目的开发依赖进行管理,通过node直接执行本地node_modules中的脚本,隔离性最好。

步骤:

  1. 在您的项目根目录执行安装:
    npm install --save-dev [email protected]
  2. 更新您的MCP配置文件,使用相对路径指向node_modules中的启动脚本。

配置示例:

"seo-mcp": {
  "timeout": 60,
  "type": "stdio",
  "command": "node",
  "args": ["./node_modules/seo-mcp-server/dist/index.js"],
  "env": {
    "SEO_MCP_AI_DETECT_API_KEY": "YOUR_5118_API_KEY"
  }
}

注意:此方法要求您的宿主环境工作目录在项目根目录,以便相对路径./node_modules/...能被正确解析。