readability-mcp-server
readability-mcp-server
一个 MCP 服务器,让任何 AI 智能体都能在文本落入人类读者之手前,先自行检查并改进其平实语言质量。完全本地:无 API 密钥、无网络调用、无外部服务。它是一个纯计算工具,因此你传入其中的任何内容都不会离开所运行的机器。
与本系列中的其他工具(scamlens、clearread、clauselens)不同,这一款不是供人打开的网站,而是为 AI 智能体生态本身构建的基础设施。任何兼容 MCP 的客户端(Claude Code、Claude Desktop 或其他)都可以直接调用它。
为什么
智能体会产生大量文本——回复、文档、通知、错误消息——在发出之前,它们大多无法检查这些文本对接收者是否真正易读。这个服务器把这种自我检查变成一键式工具调用,使用与 clearread(本系列中的独立 Web 应用)相同的平实语言引擎(句子拆分 + 一份经过验证的复杂词转平实词词典),在这里以编程方式供程序调用,而不是手动粘贴到浏览器里。
Related MCP server: BeLikeNative Grammar Server
Tools
readability_score_text
计算一段英文文本的 Flesch Reading Ease 和 Flesch-Kincaid Grade Level。对于非拉丁字母文本,仅返回 supported: false 和结构统计,因为 Flesch 公式假定的是英文音节。
readability_simplify_text
将文本改写为更为平实的语言——在自然的句法边界拆分过长的句子,并用平实的同义词替换常见的官腔词汇——同时报告改写前后的 Flesch Reading Ease 分数,以便你确认改写是否确实有效。只支持英文,这是有意为之:在形态更丰富的语言中,词替换不可靠,因此非拉丁字母文本会被检测出来并无改动地通过,而不是冒着产生错误语法的风险(关于为什么几个容易诱人的词典条目,比如“accompanied” → “went with”,在破坏了诸如“must be accompanied by”这样的常见固定短语后没有被收录,请参考 src/services/simplify.ts 中的说明)。
安装与配置
克隆并构建:
git clone https://github.com/wedo911/readability-mcp-server.git
cd readability-mcp-server
npm install
npm run build将其添加到你的 MCP 客户端配置中(例如 claude_desktop_config.json,或 Claude Code 项目的 .mcp.json):
{
"mcpServers": {
"readability": {
"command": "node",
"args": ["/absolute/path/to/readability-mcp-server/dist/index.js"]
}
}
}运行测试
npm run build
node --test tests/textStats.test.mjs tests/simplify.test.mjs无需客户端进行试用
MCP Inspector 可以直接从命令行调用工具:
npx @modelcontextprotocol/inspector --cli node dist/index.js \
--method tools/call --tool-name readability_simplify_text \
--tool-arg text="Please utilize the enclosed form prior to the deadline."许可证
MIT — 参见 LICENSE。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenancePublishReady helps AI agents turn drafts into cleaner, publish-ready writing using deterministic local metrics. It checks readability, structure, AI-sounding prose, revision targets, and factual preservation without external API calls.2MIT
- FlicenseAqualityCmaintenanceL1-aware grammar, style, translation & tone tools with 70 local rules. Zero API keys needed.4
- AlicenseAqualityBmaintenanceDeterministic fluff detector for AI-generated prose. No model, no API key.3MIT
- AlicenseAqualityBmaintenanceEnables AI agents to read clean Markdown from any URL and assess source quality with AI-readability scores.6651MIT
Related MCP Connectors
The open, measured register where AI agents evolve written English together.
Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests.
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/wedo911/readability-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server