Provides templated recording functionality that generates structured markdown documents for meetings, project summaries, learning notes, and daily standups
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-dev-record get the meeting record template for our team sync"
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.
一个专门用于记录和整理对话内容的 MCP (Model Context Protocol) 服务器，提供模板化的记录功能。
🔧 两个核心工具：
get_template_list: 获取可用的记录模板列表
get_template_detail: 获取具体模板的详细内容
📝 内置模板：
会议记录模板 (meeting-record): 用于记录会议内容、决策和行动项
项目总结模板 (project-summary): 用于总结项目进展、问题和计划
学习笔记模板 (learning-notes): 用于记录学习内容和心得体会
每日站会模板 (daily-standup): 用于记录团队每日站会内容
Related MCP server: MCP LLM Generator v2
git clone https://github.com/seenbefore/DevRecord.git
cd DevRecordnode版本16+，推荐18
npm installnpm run build{
"mcpServers": {
"devrecord": {
"command": "node",
"args": ["C:\\PATH\\TO\\PARENT\\FOLDER\\DevRecord\\build\\index.js"]
}
}
}当您对大模型说："用devrecord帮我记录一下"，大模型会：
调用 get_template_list 获取可用模板列表
根据对话内容选择合适的模板
调用 get_template_detail 获取模板详情
按照模板规范总结对话内容
生成 markdown 文档保存到 src/record/ 目录
描述: 获取所有可用的记录模板
参数: 无
返回: 模板列表，包含模板名称、文件名和描述
描述: 获取指定模板的完整内容
参数:
templateName (string): 模板名称（不含扩展名）
返回: 模板的完整markdown内容
DevRecord/
├── src/
│ ├── index.ts # MCP服务器主文件
│ ├── template/ # 模板目录
│ │ ├── meeting-record.md
│ │ ├── project-summary.md
│ │ ├── learning-notes.md
│ │ └── daily-standup.md
│ └── record/ # 生成的记录文档目录
├── build/ # 编译后的文件
├── package.json
└── tsconfig.json在 src/template/ 目录下创建新的 .md 文件
在 src/index.ts 的 getTemplateDescription 函数中添加描述
重新构建项目
TypeScript
Node.js
MCP SDK (@modelcontextprotocol/sdk)
Zod (参数验证)
确保安装了 Node.js 和 npm
使用 TypeScript 进行开发
遵循 MCP 协议规范
支持跨平台运行（Windows/Linux/macOS）
欢迎提交 Issue 或 Pull Request！
本项目基于 MIT License 开源。
获取指定模板的详细内容。templateName 参数必须使用 get_template_list 返回的 templates 中的 templateName 值。这确保了参数的准确性和一致性。返回模板的完整内容，可用于创建新的开发记录文档。如果模板不存在，会返回明确的错误信息。
| Name | Required | Description | Default |
|---|---|---|---|
| templateName | Yes | 模板文件名（不包含扩展名），必须使用 get_template_list 返回的 templates 中的 templateName |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses that the tool returns '模板的完整内容' (complete template content) and mentions error behavior: '如果模板不存在，会返回明确的错误信息' (if template doesn't exist, returns clear error message). However, it doesn't describe authentication needs, rate limits, or other behavioral traits like response format or performance characteristics.
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 efficiently structured with four sentences that each serve distinct purposes: stating the core function, specifying parameter requirements, describing the return value, and explaining error behavior. There's no wasted text, and key information appears early.
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 single-parameter read operation with no annotations and no output schema, the description provides good coverage: purpose, parameter constraints, return value description, and error behavior. However, it doesn't fully explain what '完整内容' (complete content) includes or the response format, leaving some ambiguity about the output.
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 baseline is 3. The description adds meaningful context about the templateName parameter: it must come from get_template_list responses and ensures '参数的准确性和一致性' (parameter accuracy and consistency). This provides practical usage guidance beyond the schema's technical description, elevating the score.
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 clearly states the tool's purpose: '获取指定模板的详细内容' (Get detailed content of a specified template). It specifies the verb ('获取' - get) and resource ('模板的详细内容' - template details). However, it doesn't explicitly differentiate from its sibling tool 'get_template_list' beyond mentioning that templateName must come from that tool's response.
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?
The description provides explicit usage guidance: 'templateName 参数必须使用 get_template_list 返回的 templates 中的 templateName 值' (templateName parameter must use the templateName value from templates returned by get_template_list). It clearly states when to use this tool (to get template details) and references the alternative/sibling tool for obtaining valid parameter values.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
获取可用的开发记录模板列表。返回包含模板名称、文件名和描述的结构化数据。返回的 templates 数组中每个模板都有 templateName 字段，这是后续调用 get_template_detail 时必需的参数。使用此工具来发现可用的模板，然后使用返回的 templateName 来获取具体模板内容。
| Name | Required | Description | Default |
|---|---|---|---|
| dummy | No | Dummy parameter for no-parameter tools |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it returns structured data with specific fields (templateName, filename, description), explains the output format (templates array), and clarifies that templateName is required for subsequent calls to get_template_detail. However, it doesn't mention potential limitations like pagination or rate limits.
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 perfectly concise with three sentences that each serve a distinct purpose: stating the tool's function, describing the return structure, and providing usage guidance. There is zero wasted text, and information is front-loaded appropriately.
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?
Given the tool's low complexity (no real parameters, no output schema, no annotations), the description is nearly complete. It explains what the tool does, what it returns, and how to use the output. The only minor gap is lack of explicit mention that this is a read-only operation, though that's reasonably inferred from the 'get' prefix and list functionality.
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?
The input schema has 100% description coverage but only documents a dummy parameter. The description correctly indicates this is essentially a no-parameter tool by not mentioning any required inputs, adding value beyond the schema. It compensates for the dummy parameter's lack of real meaning by focusing on the tool's parameterless nature.
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 clearly states the tool's purpose with specific verbs ('获取可用的开发记录模板列表') and resource ('模板列表'). It distinguishes from its sibling tool 'get_template_detail' by explaining this tool discovers available templates while the sibling gets specific template content.
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?
The description provides explicit guidance on when to use this tool ('使用此工具来发现可用的模板') and when to use the alternative ('然后使用返回的 templateName 来获取具体模板内容'). It clearly establishes the workflow relationship with the sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clearly distinct purposes: get_template_list retrieves a list of available templates with metadata, while get_template_detail fetches the detailed content of a specific template. There is no overlap or ambiguity between them, as one is for discovery and the other for content retrieval.
Both tools follow a consistent verb_noun pattern (get_template_list and get_template_detail), using the same verb 'get' and a clear noun structure. This makes the naming predictable and easy to understand across the tool set.
With only 2 tools, the server feels thin for a development record domain, as it lacks operations like creating, updating, or deleting templates or records. While the tools cover basic retrieval, the scope seems limited, potentially requiring agents to work around missing functionality.
The tool surface is significantly incomplete for a development record system. It only provides read operations (list and detail retrieval) with no ability to create, update, or delete templates or records. This leaves obvious gaps that could cause agent failures when trying to perform full lifecycle management.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Speech-to-Text
An MCP server for deep research or task groups
An MCP server that provides tools to discover and retrieve podcast episodes transcripts.
An MCP memory server. One memory your agents share — across models, devices and apps.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/seenbefore/DevRecord'
If you have feedback or need assistance with the MCP directory API, please join our Discord server