avoid-ai-writing-mcp
avoid-ai-writing-mcp
一个本地、确定性的 MCP 服务器,用于通过已发布的 avoid-ai-writing-detector 审计文稿。
它提供两个只读工具:
score_text返回一个紧凑的评分、分类、置信度和计数。audit_text额外提供每个被标记的模式、建议的替代方案、统计信息以及高亮的句子区域。
该服务器不进行任何网络调用,也不使用语言模型。文本始终留在本地 MCP 进程内。评分只是启发式的写作模式信号,并不能证明文本由人类还是模型撰写。
环境要求
Node.js 18 或更高版本
支持本地 stdio 服务器的 MCP 主机
Related MCP server: Byakugan: Private, open-source AI-text checker
从 GitHub 运行
将该服务器添加到 Claude Code:
claude mcp add avoid-ai-writing -- npx -y github:conorbronsdon/avoid-ai-writing-mcp或者将其添加到 MCP JSON 配置中:
{
"mcpServers": {
"avoid-ai-writing": {
"command": "npx",
"args": ["-y", "github:conorbronsdon/avoid-ai-writing-mcp"]
}
}
}当这个包发布到 npm 后,将 GitHub 包引用替换为 avoid-ai-writing-mcp。
该包使用 stdio 进行协议消息。它不会打开端口,也不会将输入发送到任何 API。
工具输入
两个工具都接收:
字段 | 类型 | 必填 | 说明 |
| string | 是 | 要在本地评估的文本(最多 100,000 个字符)。 |
| enum | 否 |
|
technical 模式可以减少代码相关写作中常见模式带来的噪音。其他模式则保留检测器上下文相关的行为。
开发
npm install
npm test
npm run inspectnpm run inspect 会针对本地 stdio 入口启动官方 MCP Inspector。
范围
本包有意不提供重写工具。重写需要编辑判断,而且通常需要托管模型;添加重写会破坏该服务器确定性、本地化、隐私保护的约定。
许可
MIT
Maintenance
Tools
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI attribution audits and quick transparency checks on written content, providing authorship analysis and segment breakdowns for editorial review.21MIT
- AlicenseAqualityBmaintenanceA private, open-source AI-text checker. Get a read on whether text looks AI-written, the exact AI-tell spans to fix, a reuse check, and a grammar pass.4MIT
- FlicenseNot gradedqualityAmaintenanceProvides tools to analyze local PDFs and CSVs (page count, text search, scoring, column stats) with strict refusal to guess ambiguous data. Requires a paid license.
- AlicenseAqualityAmaintenanceBilingual (EN/ES) AI-writing detection that shows the evidence instead of a percentage: named tells with line and column, hidden-character inspection, and citation cross-checking against a document's own bibliography. Seven of its nine tools run entirely locally and never touch the network.1020MIT
Related MCP Connectors
Find AI-isms with evidence and fingerprint a writing voice from samples. 3 of 5 free.
Six tools for SEO and AI-readability audits. 91 checks, 11 score modules.
Prose linter + AI-slop detector: weasel words, passive voice, hedging, and research-cited AI tells
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/conorbronsdon/avoid-ai-writing-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server