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., "@mcp-server-memos create a note about weekly report"
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.
这是一个 MCP 服务器,用于与 Memos 笔记服务进行交互。通过这个服务器,你可以在任何支持 MCP 协议的客户端中使用自然语言与 Memos 进行交互。
🔍 搜索笔记
✨ 创建新笔记(支持设置可见性)
📖 获取笔记内容
✏️ 更新笔记内容
🔐 使用访问令牌进行安全认证
Related MCP server: Memos MCP Server
你可以通过以下两种方式之一配置服务器:
环境变量:
MEMOS_URL=https://your-memos-server # Memos 服务器地址
MEMOS_TOKEN=your_access_token # 访问令牌命令行参数:
--memos_url=https://your-memos-server
--memos_token=your_access_token在 Cursor 的配置文件中(通常位于 ~/.cursor/mcp.json)添加以下配置:
{
"mcpServers": {
"mcp-server-memos": {
"command": "npx",
"args": ["-y","@chenyqthu/mcp-server-memos"],
"env": {
"MEMOS_URL": "https://your-memos-server",
"MEMOS_TOKEN": "your_access_token"
}
}
}
}本服务已支持托管在 MCP.so 上，你可以直接使用托管版本而无需在本地配置和运行服务器。
在使用 MCP.so 托管版本时，只需提供以下参数：
MEMOS_URL: 你的 Memos 服务器地址
MEMOS_TOKEN: 你的 Memos 访问令牌
克隆仓库:
git clone https://github.com/your-username/mcp-server-memos.git
cd mcp-server-memos安装依赖:
npm install创建 .env 文件:
MEMOS_URL=https://your-memos-server
MEMOS_TOKEN=your_access_token运行服务:
npm run inspector服务器提供以下工具:
search_memo - 搜索笔记
key_word: 搜索关键词
create_memo - 创建新笔记
content: 笔记内容
visibility: 笔记可见性 (PUBLIC/PROTECTED/PRIVATE, 默认: PRIVATE)
get_memo - 获取指定笔记
name: 笔记ID (格式: memos/{id})
update_memo - 更新指定笔记
name: 笔记ID (格式: memos/{id})
content: 新的笔记内容
在 Cursor 中,你可以这样使用:
创建笔记:
帮我记录一条笔记: 今天学习了 MCP Server 开发搜索笔记:
搜索包含 "MCP" 关键词的笔记使用 TypeScript 开发
支持热重载开发 (npm run watch)
该项目已配置为可以托管在 MCP.so 平台上。通过托管，你可以：
无需本地安装和配置
稳定的服务可用性
集成到 MCP Playground 中
确保你的代码已托管在 GitHub 上并使用商业友好的开源许可证（MIT、Apache 等）
确保代码不依赖于读取本地数据（如文件、本地数据库等）
通过 MCP.so 平台提交你的服务器
审核通过后，你的服务器将显示在 MCP Playground 中
请妥善保管你的访问令牌
在生产环境中使用时,建议使用环境变量而不是命令行参数传递敏感信息
Create a new memo
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | The content of the memo | |
| visibility | No | Memo visibility | PRIVATE |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only states creation, lacking details on side effects, required permissions, or what happens on invocation. The schema supplements partially but does not cover behavioral implications.
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?
Ultra-concise: one sentence with no wasted words. Front-loaded with the action. Efficient for an agent to parse.
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?
With 2 simple params and no output schema, the description is brief. It does not specify return value (e.g., created memo ID or object), which could aid usability. Adequate but not complete.
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 coverage is 100% (all params described in schema). The description adds no extra meaning beyond the schema, but the schema itself is clear. Baseline score of 3 is appropriate.
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 'Create a new memo' clearly states the action and resource. It distinguishes from sibling tools (get, search, update) by the verb 'create', which is distinct enough.
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 on when to use this tool versus alternatives like update_memo. The description does not provide when-not or alternative contexts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a specific memo by ID
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The name/ID of the memo (format: memos/{id}) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It does not mention idempotency, error behavior (e.g., if memo not found), or whether the tool is read-only. The description is too brief to disclose key behavioral traits.
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?
Single, clear sentence with no extraneous words. Front-loads the action and resource.
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 simple one-parameter get tool, the description is minimally adequate but lacks details on output or error handling. With no output schema, some return value description would improve completeness.
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 coverage is 100% and the parameter 'name' is already described with format 'memos/{id}'. The description adds 'by ID' but provides no additional semantics beyond the schema.
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 explicitly states the action ('Get') and the resource ('a specific memo by ID'). It clearly distinguishes from sibling tools (create, search, update) which have different verbs or scopes.
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 on when to use this tool versus alternatives (e.g., search_memo). It assumes the agent already has the ID, but does not explain prerequisites or cases where search might be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for memos using keywords
| Name | Required | Description | Default |
|---|---|---|---|
| key_word | Yes | The keywords to search for in memo content |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states that it 'searches for memos using keywords' without detailing return format, match behavior (fuzzy/exact), case sensitivity, pagination, or sorting. The agent has minimal insight into the tool's behavior.
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, front-loaded sentence with no redundancy. Every word serves a purpose, making it efficiently scannable for an AI agent.
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 (single parameter, no output schema, no annotations), the description is minimally adequate. However, it lacks details on return value structure or behavior, which a simple tool should provide to ensure correct usage.
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 schema covers 100% of parameters, so the baseline is 3. The description adds no additional meaning beyond the schema's own description: it merely repeats the parameter purpose. No extra context or constraints are provided.
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 action ('Search for memos') and the method ('using keywords'), distinguishing it from sibling tools create_memo, get_memo, and update_memo. This leaves no ambiguity about the tool's purpose.
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 no guidance on when to use this tool versus alternatives. It does not mention when not to use it, nor does it differentiate from get_memo (which retrieves by ID) or other search methods. This lack of context may lead to incorrect tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update a specific memo by ID
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The name/ID of the memo (format: memos/{id}) | |
| content | Yes | The content of the memo |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It only states 'Update a specific memo by ID', which indicates mutation but does not disclose idempotence, permission requirements, error behavior, or whether it overwrites or merges fields. The minimal disclosure leaves significant gaps.
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, front-loaded sentence that efficiently conveys the core purpose. It is concise with no wasted words, though additional detail could be structured without losing efficiency.
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 has 2 required parameters, no output schema, and no annotations, the description is too brief. It omits important context such as return value, update semantics (full replacement vs partial), and error conditions, making it incomplete for effective agent use.
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% (both parameters have clear descriptions), so the baseline is 3. The tool description adds no parameter information beyond the schema, but it does not detract either.
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 action 'Update' and the resource 'memo' with identification by ID. However, it lacks explicit differentiation from sibling tools like create_memo (which creates) and get_memo (which reads), but the verb itself implies modification.
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 versus alternatives such as create_memo or get_memo. There is no mention of prerequisites, exclusions, or typical scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.1.0create_memoget_memosearch_memoupdate_memoScored across 4 tools
Each tool has a unique function (create, get, search, update) with no overlaps, making selection unambiguous.
All tools follow the same verb_noun pattern (create_memo, get_memo, search_memo, update_memo), ensuring predictable naming.
With 4 tools, the set is concise and well-scoped for basic memo management, fitting the typical range for such a server.
The set covers create, read, search, and update but lacks a delete tool, which is a notable gap for full lifecycle management.
Search, read, create and edit your Memol notes from Claude. Team note-taking with AI search.
Connect AI to your flomo notes. Search, create, edit notes and manage tags via MCP.
Securely search, create, and organize your Mem notes and collections from AI assistants.
Create, search and manage Knowtis collaborative notes from AI assistants.
