Academic Polish MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Academic Polish MCP 润色这段论文段落,保持引文和数字不变:本研究使用100份问卷,结果表明该方法可能有效[1]。"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Academic Polish MCP
一个轻量、保守的论文段落润色 MCP。它只提供一个工具:
polish_academic_text:润色中英文论文段落,同时检查常见引文、数字、LaTeX 公式、URL、DOI 和指定术语是否被改动。默认检测到变化时保留原文,拒绝采用候选稿。
边界
提示模型保持事实、数据、结论和参考文献;自动检查不能替代语义和事实核验。
不替代导师或作者进行学术判断。
单次最多处理 12,000 个字符,建议按段落或小节调用。
需要一个兼容 OpenAI Chat Completions 的模型 API Key。
不包含全文文件解析、查重和翻译。支持轻度、标准、深度和压缩模式。
Related MCP server: paeg-lang-style
环境变量
变量 | 必填 | 默认值 |
| 是 | 无 |
| 否 |
|
| 否 |
|
| 否 |
|
模型默认值依据 DeepSeek 官方接入文档。API 调用会消耗模型账户额度;论文段落将发往 LLM_BASE_URL 对应服务。代码不保存论文文本,但宿主平台和模型服务的日志策略由各自配置决定。
本地运行
需要 Node.js 20 或更高版本。
npm ci
npm test
npm start测试使用本机模拟接口,不需要真实 Key,也不消耗模型额度。真实调用前须在进程环境中设置 LLM_API_KEY;.env.example 只是示例,不会自动加载。stdio MCP 启动后会等待宿主通过 stdin/stdout 通信,这是正常现象。
平台 npx 配置
平台须支持 Node.js 20+、npm 和 Git,并能访问 GitHub、npm 包源和模型接口。选择 npx,服务名填写“论文段落润色”,描述填写“润色论文段落,保留数字和引文,返回修改说明”。固定版本配置见 mcp-config.example.json:
{
"mcpServers": {
"academic-polish": {
"command": "npx",
"args": ["-y", "git+https://github.com/212Yggg/academic-polish-mcp.git#v1.0.1"],
"env": {
"LLM_API_KEY": "REPLACE_IN_PLATFORM_ONLY",
"LLM_BASE_URL": "https://api.deepseek.com",
"LLM_MODEL": "deepseek-flash",
"LLM_TIMEOUT_MS": "90000"
}
}
}
}仅在平台环境变量中替换 Key 占位符,再点击“保存并部署”。工具列表出现 polish_academic_text 后挂载到智能体。部署成功与真实模型调用成功需分别测试。GitHub 安装通过 prepare 编译 TypeScript,首次部署需要等待依赖安装。
工具输入示例
{
"text": "本研究使用100份问卷,结果表明该方法可能有效[1]。",
"mode": "standard",
"language": "zh-CN",
"discipline": "教育学",
"target_style": "硕士论文,正式且克制",
"preserve_terms": ["100份问卷", "[1]"],
"strict_preservation": true
}返回值包括:
polished_textchange_summaryrisk_flagspreservation_check:passed(自动检查未发现差异)、blocked(已保留原文)或not_checked(用户关闭检查)requires_human_review
requires_human_review 始终为 true。自动检查无法覆盖所有单位、变量、专有名词及语义变化;passed 不表示事实已经核验。language 控制修改说明和风险提示的语言,正文保留原语种。
智能体调用规则
用户提供自己的论文段落并要求润色、修改表述或压缩时,调用 polish_academic_text。
text 原样传入用户要修改的正文,默认 mode=standard、strict_preservation=true。
只展示工具返回的修改稿、主要修改说明和需要作者确认的问题,不自行补充研究事实。
如果 preservation_check=blocked,说明候选稿有受保护内容变化,当前返回原文。
如果调用失败,报告失败,不声称完成润色。不写入文献表,不自动修改原论文文件。安全提醒
不要把 API Key 写入 GitHub 仓库或发送到聊天中。Key 只应填写在 MCP 平台受控的环境变量/密钥配置中;若只能在 JSON 的 env 中填写,确认只有授权管理员可查看。截图时将 Key 完全遮挡。LLM_BASE_URL 不应包含 /chat/completions 或凭据;远程接口必须使用 HTTPS。
Available Tools
1 toolpolish_academic_textA
润色用户提供的中英文论文段落,返回修改稿、修改说明和风险提示。默认检查常见数字、引文、LaTeX公式、URL、DOI及指定术语;检测到变化时保留原文。文本会发往服务端配置的模型API。不生成新事实或参考文献,不读写文献表。
Inputs: text (required), mode, language, discipline, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is nothing to confuse it with; its purpose (polishing academic paragraphs and returning the revision, change notes, and risk warnings) is stated explicitly.
The single name 'polish_academic_text' is a clear verb_noun snake_case identifier with no competing conventions to clash with.
A one-tool surface is thin for a reusable server; the rubric treats 1-2 tools as borderline, even though the stated scope (text polishing) is genuinely narrow.
The core lifecycle of 'submit paragraph, get revised text plus explanation and risk flags' is fully covered, but there is no batch mode, no segment-level or diff-only operation, and no way to manage the custom terminology list referenced in the description.
Maintenance
Related MCP Connectors
Compress prose for LLM context windows. Per-call USDC billing, signed receipt.
Rewrite drafts in your own words and a natural voice while preserving meaning. Ink OAuth required.
Rewrite text so it reads naturally, or paraphrase it in a chosen style. Works in many languages.
Check if references exist or were retracted, look up journal AI policies, and preview manuscripts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA sophisticated academic manuscript revision system that provides surgical, line-anchored editing tools through MCP, designed for precise manuscript revisions while maintaining word count and semantic integrity.1MIT
- AlicenseNot gradedqualityBmaintenanceEnforces Chinese language style norms on LLM outputs via rule-based constraints, forbidden-word filtering, and rewriting, while offering tools for grammar checking, AI-taste detection, and style prompt assembly.MIT
- AlicenseAqualityCmaintenanceProvides AI models with tools to proofread and format Chinese text before delivery, covering typos, punctuation, casing, spacing, and platform-specific character limits. It runs as a zero-dependency MCP service so the model checks and fixes its own Chinese writing automatically.41MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI hosts to check text for grammar, spelling, and style errors, measure readability, and generate tone-adjusted rewrites through structured tool calls. Every tool returns predictable, typed output for reliable routing and results.MIT