MCP-Server-Inbox
This server allows you to create notes in the inBox service via MCP clients.
Create notes with optional titles in Markdown format (including images via URLs)
Supports up to 50 API requests per day with a 3000 character limit per note
Access built-in Inspector tool for debugging and monitoring
Configure for use in Cursor AI and other MCP-compatible clients
Supports creating notes in Markdown format with the inBox note-taking service, allowing users to save and organize notes with optional titles through natural language conversations.
Click on "Install 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., "@MCP-Server-Inbox记录一下:今天完成了MCP服务器开发,支持笔记创建功能"
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.
MCP-Server-Inbox
MCP 服务对接 inBox 笔记 API,实现在任意 MCP 客户端以对话形式创建笔记的功能。
功能介绍
接入 inBox 笔记 API
提供 MCP 服务发现接口
支持通过 MCP 客户端创建笔记
支持设置笔记标题(可选)
支持 Inspector 调试工具
Related MCP server: MCP Notes Server
前置条件
Node.js 18+
inBox 笔记 API (PRO 功能)
支持 MCP 协议的客户端(如 Cursor AI)
安装与使用
方法一:使用 npx 运行
# 运行服务
npx mcp-server-inbox --inbox_user_token=https://inbox.gudong.site/api/inbox/your_token_here
# 使用环境变量
INBOX_USER_TOKEN=https://inbox.gudong.site/api/inbox/your_token_here npx mcp-server-inbox方法二:本地构建
克隆代码仓库
git clone https://github.com/maoruibin/mcp-server-inbox.git
cd mcp-server-inbox安装依赖
npm install构建项目
npm run build运行服务
# 运行服务
node build/index.js --inbox_user_token=https://inbox.gudong.site/api/inbox/your_token_here
# 使用环境变量
INBOX_USER_TOKEN=https://inbox.gudong.site/api/inbox/your_token_here node build/index.js调试与开发
使用 Inspector
项目内置了 MCP Inspector 工具,可以帮助调试和监控服务运行状态:
npm run inspector运行后可以在浏览器中访问 http://localhost:5173 查看服务运行状态和调试信息。
在 MCP 客户端中配置
Cursor AI
打开 Cursor 的 MCP 服务配置文件(通常位于
~/.cursor/mcp.json)添加 mcp-server-inbox 的配置:
{
"mcpServers": {
"mcp-server-inbox": {
"command": "npx",
"args": [
"mcp-server-inbox"
],
"env": {
"INBOX_USER_TOKEN": "your api path"
}
}
}
}其他 MCP 客户端
请参考对应 MCP 客户端的配置文档,添加类似的配置信息。
使用示例
在支持 MCP 的客户端中,您可以使用自然语言与 AI 对话,来创建笔记:
"记录一下:今天学习了 MCP 开发"
"帮我记笔记,标题是「TypeScript学习」:TypeScript 的高级类型包括 Partial、Required、Pick 等"
"写到 inBox:明天需要完成项目文档编写"
API 说明
write_note
描述:将笔记内容写入到 inBox
参数:
title:笔记标题(可选)
content:笔记内容(Markdown 格式),最多 3000 字符
返回:
成功:返回包含成功信息的对象
失败:抛出相应的错误信息
inBox API 说明
本项目依赖 inBox 的 API 服务,具体说明如下:
接口信息
接口地址:
https://app.gudong.site/api/inbox/${userToken}请求方式:
POSTContent-Type:
application/json请求频率:每天最多 50 条
请求参数
参数 | 类型 | 是否必填 | 说明 |
title | 字符串 | 否 | 笔记标题 |
content | 字符串 | 是 | 笔记内容,最多 3000 字符 |
使用示例
创建普通笔记:
npx mcp-server-inbox --inbox_user_token=https://inbox.gudong.site/api/inbox/your_token_here创建带标题的笔记:
# 在对话中指定标题
"帮我记笔记,标题是「TypeScript学习」:TypeScript 的高级类型包括 Partial、Required、Pick 等"响应格式
{
"code": 0,
"msg": "已提交,请打开inBox查看笔记"
}说明:code 为 0 表示请求成功,非零状态均为失败
图片支持
inBox API 支持解析 Markdown 格式的图片标签。您可以在笔记内容中添加 markdown 格式的图片链接,例如:
今天天气很好,注意:API 不支持直接上传图片,需要先将图片上传到图床后使用图片链接
更多 API 详细信息请参考:inBox API 文档
处理逻辑
当用户通过 MCP 客户端发送创建笔记的请求时,服务会根据以下逻辑处理:
解析用户输入,识别标题(如有)和内容
调用 inBox API,直接传递
title和content两个参数返回处理结果和笔记内容摘要
用户可以在对话中明确指定标题,例如:"帮我记笔记,标题是「TypeScript学习」:这是内容...",服务会自动提取标题部分。
限制说明
inBox API 请求频率限制为每天最多 50 条
笔记内容最多支持 3000 字符
需要 inBox PRO 用户才能使用 API 功能
获取 inBox API 配置
打开 inBox 应用
进入【设置】->【账户】->【Api】
获取您的专属 API 配置信息
贡献指南
欢迎提交 Issue 和 Pull Request 来帮助改进这个项目。在提交 PR 之前,请确保:
代码通过 TypeScript 编译
所有功能都经过测试
更新相关文档
更新日志
v0.1.0
初始版本发布
支持基本的笔记创建功能
支持 Token 和完整 URL 两种配置方式
添加 Inspector 调试工具支持
作者
gudong - 个人主页
相关项目
inBox - 简单好用的笔记服务
MCP Protocol - Model Context Protocol 规范
许可证
MIT
Available Tools
1 toolwrite_noteC
Write note to inBox
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Optional title of the note | |
| content | Yes | Text content of the note with markdown format |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states the action without behavioral details. It doesn't disclose permissions needed, side effects, error conditions, or response format. 'Write' implies mutation, but no further context is given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It is appropriately sized for a simple tool and front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It lacks behavioral context, usage guidelines, and details on what happens after writing (e.g., success response, error handling). The high schema coverage doesn't compensate for these gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents parameters (title and content). The description adds no parameter semantics beyond what the schema provides, meeting the baseline of 3 for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Write note to inBox' states the action (write) and target (note to inBox), but is vague about what 'inBox' refers to (a specific location, application, or system). It doesn't distinguish from siblings since none exist, but the purpose lacks specificity beyond basic verb+resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool, such as prerequisites, alternatives, or context. The description only states what it does, with no indication of appropriate scenarios or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
- First observed
write_note
TDQS
With only one tool, there is no possibility of confusion or overlap between tools, making disambiguation perfect. The tool's purpose is singular and clearly defined as writing notes to an inbox.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'write_note' follows a clear verb_noun pattern, and there are no other tools to compare or create inconsistency with.
A single tool is too few for a server named 'MCP-Server-Inbox', which suggests a domain involving inbox management. This minimal toolset likely leaves significant gaps in functionality, such as reading, updating, or deleting notes, making it inappropriate for the implied scope.
The tool surface is severely incomplete for an inbox server. It only provides a 'write_note' tool, lacking essential operations like reading notes, listing notes, updating notes, deleting notes, or managing inbox states, which will cause agent failures in handling inbox workflows.
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 Connectors
An MCP server that used to create notes
Google Keep-style notes app with an MCP server for AI agents to read/write notes.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Save notes in seconds. Your AI can then search, read, write and tag them over MCP.
Related MCP Servers
- AlicenseAqualityDmaintenanceA simple note-taking MCP server for recording and managing notes with AI models.42236GPL 2.0
- AlicenseBqualityDmaintenanceAn MCP server for managing and persisting notes, offering CRUD operations, note summarization, and resource-based access via a note:// URI scheme.47MIT
- FlicenseBqualityDmaintenanceA simple note-taking MCP server that stores notes and can generate summaries of stored content.4-
- AlicenseNot gradedqualityDmaintenanceA proof-of-concept MCP server for AI assistant note-taking, enabling adding notes, fetching the latest note, and summarizing all notes.5MIT
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/maoruibin/mcp-server-inbox'
If you have feedback or need assistance with the MCP directory API, please join our Discord server