Skip to main content
Glama
onigeya

SiYuan Note MCP Server

by onigeya
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

SiYuan Note MCP Server

一个 MCP 服务器实现，提供与思源笔记系统的集成，使 AI 模型能够访问和操作笔记数据。

An MCP server implementation that provides integration with the SiYuan Note system, enabling AI models to access and manipulate note data.

功能特性 | Features

  • 笔记本管理 | Notebook Management

  • 文档操作 | Document Operations

  • 内容块控制 | Block Control

  • 文件和资源管理 | File and Asset Management

  • SQL 查询支持 | SQL Query Support

  • 属性管理 | Attribute Management

  • 导出和转换 | Export and Conversion

  • 系统功能 | System Functions

Related MCP server: MCP Notes Server

命令列表 | Command List

所有命令都支持使用 help 查询获取详细说明。例如：

All commands support detailed documentation via the help command. For example:

{
  "type": "help",
  "params": {
    "type": "block.insertBlock"
  }
}

资源管理 | Asset Management

  • assets.uploadAssets - 上传资源文件 | Upload assets

属性管理 | Attribute Management

  • attr.setBlockAttrs - 设置块属性 | Set block attributes

  • attr.getBlockAttrs - 获取块属性 | Get block attributes

内容块操作 | Block Operations

  • block.insertBlock - 插入内容块 | Insert a block

  • block.updateBlock - 更新内容块 | Update block content

  • block.deleteBlock - 删除内容块 | Delete a block

  • block.moveBlock - 移动内容块 | Move a block

  • block.getBlockKramdown - 获取块的 Markdown 内容 | Get block Kramdown content

格式转换 | Format Conversion

  • convert.pandoc - 使用 Pandoc 转换内容 | Convert content using Pandoc

导出功能 | Export Functions

  • export.exportNotebook - 导出笔记本 | Export notebook

  • export.exportDoc - 导出文档 | Export document

文件操作 | File Operations

  • file.getFile - 获取文件内容 | Get file content

  • file.putFile - 写入文件内容 | Put file content

  • file.removeFile - 删除文件 | Remove file

  • file.readDir - 读取目录内容 | List files in directory

文档树操作 | File Tree Operations

  • filetree.createDocWithMd - 使用 Markdown 创建文档 | Create document with Markdown

  • filetree.renameDoc - 重命名文档 | Rename document

  • filetree.removeDoc - 删除文档 | Remove document

  • filetree.moveDocs - 移动文档 | Move documents

  • filetree.getHPathByPath - 获取文档可读路径 | Get document HPath by path

  • filetree.getHPathByID - 通过 ID 获取文档可读路径 | Get document HPath by ID

网络代理 | Network Proxy

  • network.forwardProxy - 网络请求代理 | Forward proxy request

笔记本管理 | Notebook Management

  • notebook.lsNotebooks - 列出所有笔记本 | List all notebooks

  • notebook.openNotebook - 打开笔记本 | Open notebook

  • notebook.closeNotebook - 关闭笔记本 | Close notebook

  • notebook.renameNotebook - 重命名笔记本 | Rename notebook

  • notebook.createNotebook - 创建笔记本 | Create notebook

  • notebook.removeNotebook - 删除笔记本 | Remove notebook

  • notebook.getNotebookConf - 获取笔记本配置 | Get notebook configuration

  • notebook.setNotebookConf - 设置笔记本配置 | Set notebook configuration

通知提醒 | Notifications

  • notification.pushMsg - 发送消息通知 | Push message notification

  • notification.pushErrMsg - 发送错误通知 | Push error message notification

查询功能 | Query Functions

  • query.sql - 执行 SQL 查询 | Execute SQL query

  • query.block - 通过 ID 查询块 | Query block by ID

搜索功能 | Search Functions

  • search.fullTextSearch - 全文搜索 | Full text search

SQL 查询 | SQL Query

  • sql.sql - 执行 SQL 查询 | Execute SQL query

系统功能 | System Functions

  • system.getBootProgress - 获取启动进度 | Get boot progress

  • system.getVersion - 获取系统版本 | Get system version

  • system.getCurrentTime - 获取当前时间 | Get current time

模板功能 | Template Functions

  • template.renderTemplate - 渲染模板 | Render template

  • template.renderSprig - 渲染 Sprig 模板 | Render Sprig template

使用说明 | Usage

环境变量配置 | Environment Variables

服务器需要配置以下环境变量： The server requires the following environment variables:

  • SIYUAN_TOKEN - 思源笔记 API 令牌（必需）| SiYuan Note API token (required)

    • 在思源笔记设置 - 关于 中查看 | Check in SiYuan Note Settings - About

    • 用于 API 认证 | Used for API authentication

在 Claude Desktop 中使用 | Using in Claude Desktop

将以下配置添加到 claude_desktop_config.json： Add the following configuration to claude_desktop_config.json:

{
  "mcpServers": {
    "siyuan": {
      "command": "npx",
      "args": [
        "-y",
        "@onigeya/siyuan-mcp-server"
      ],
      "env": {
        "SIYUAN_TOKEN": "your-siyuan-token"
      }
    }
  }
}

本地运行 | Local Run

  1. 安装依赖 | Install dependencies:

pnpm install

  1. 设置环境变量 | Set environment variables:

# Windows
set SIYUAN_TOKEN=your-siyuan-token

# Linux/macOS
export SIYUAN_TOKEN=your-siyuan-token

  1. 启动服务 | Start service:

pnpm start

Docker 运行 | Docker Run

docker run --rm -i \
  -e SIYUAN_TOKEN=your-siyuan-token \
  mcp/siyuan

构建 | Build

环境要求 | Requirements

  • Node.js >= 23.10.0

  • pnpm

本地构建 | Local Build

pnpm build

Docker 构建 | Docker Build

docker build -t mcp/siyuan .

许可证 | License

本项目基于 ISC 许可证发布。这意味着你可以自由使用、修改和分发本软件，但需要遵守 ISC 许可证的条款和条件。详细信息请参见项目仓库中的 LICENSE 文件。

This project is released under the ISC License. This means you can freely use, modify, and distribute this software, subject to the terms and conditions of the ISC License. For detailed information, please refer to the LICENSE file in the project repository.

相关资源 | Related Resources

Available Tools

3 tools
executeCommandC

执行指定的命令

ParametersJSON Schema
NameRequiredDescriptionDefault
paramsNo命令参数
typeYes命令类型

TDQS

C2/5.0
Behavior1/5

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. '执行指定的命令' (Execute the specified command) implies a potentially destructive or mutating operation, but provides zero information about permissions required, side effects, safety considerations, rate limits, or what happens upon execution. This leaves the agent completely in the dark about critical 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - a single phrase in Chinese. While this represents severe under-specification rather than ideal conciseness, according to the scoring framework, conciseness is evaluated separately from completeness. The description contains zero wasted words and is front-loaded with its limited information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a command execution tool with no annotations, no output schema, and a description that provides almost no useful information, this description is completely inadequate. The agent cannot understand what commands are available, what they do, what permissions are required, what happens upon execution, or how to interpret results. This represents a critical failure in contextual completeness for a potentially powerful/destructive tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, with both parameters ('type' and 'params') having descriptions in the schema. The tool description adds no additional meaning about parameters beyond what the schema already provides. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no parameter information in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description '执行指定的命令' (Execute the specified command) is a tautology that essentially restates the tool name 'executeCommand' in Chinese. It provides no specific information about what kind of commands are executed, what resources are affected, or how this differs from sibling tools like 'queryCommands'. The purpose remains vague and indistinguishable from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides absolutely no guidance on when to use this tool versus alternatives like 'queryCommands' or 'help'. There is no mention of appropriate contexts, prerequisites, or exclusions. The agent receives no help in determining when this tool is the correct choice among available options.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

helpC

获取命令的帮助信息

ParametersJSON Schema
NameRequiredDescriptionDefault
typeYes命令类型

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states what the tool does ('get help information') without adding context on behavioral traits such as whether it's read-only, if it requires specific permissions, what the output format might be, or any rate limits. It's minimal and doesn't compensate for the lack of annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence ('获取命令的帮助信息'), which is appropriately sized and front-loaded. It's concise with no wasted words, though it could be more informative. The structure is clear but minimal, earning a high score for efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (a help tool with one parameter) and lack of annotations or output schema, the description is incomplete. It doesn't explain what 'help information' includes, how it relates to sibling tools, or what the tool returns. For a tool with no structured output and minimal behavioral context, it should provide more guidance to be fully helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the parameter 'type' described as '命令类型' (command type). The description adds no meaning beyond this, as it doesn't explain what 'type' entails or provide examples. With high schema coverage, the baseline is 3, and the description doesn't enhance or detract from the schema's information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description '获取命令的帮助信息' translates to 'Get help information for commands,' which states a purpose but is vague. It specifies a verb ('获取' - get) and resource ('帮助信息' - help information), but doesn't clarify what 'commands' refer to or how this differs from siblings like 'executeCommand' or 'queryCommands.' It's not tautological, but lacks specificity for sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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. There are sibling tools like 'executeCommand' and 'queryCommands,' but the description doesn't mention them or suggest contexts for usage (e.g., when you need help vs. executing a command). It's a basic statement of function with no exclusions or alternatives implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

queryCommandsC

查询可用的命令列表

ParametersJSON Schema
NameRequiredDescriptionDefault
namespaceNo命令命名空间过滤
typeNo命令名称过滤

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states what the tool does ('查询可用的命令列表') without revealing any behavioral traits such as whether this is a read-only operation, what format the output returns, whether there are rate limits, authentication requirements, or error conditions. For a tool with no annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - a single phrase '查询可用的命令列表' that directly states the tool's purpose with zero wasted words. It's appropriately sized for a simple query tool and front-loaded with the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there are no annotations and no output schema, the description is incomplete. While the tool appears to be a simple read operation (querying available commands), the description doesn't explain what the return format looks like, whether results are filtered/paginated, or any other behavioral aspects. For a tool with 2 parameters and no structured output documentation, the description should provide more context about what users can expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage (both parameters 'namespace' and 'type' are documented in the schema as '命令命名空间过滤' and '命令名称过滤' respectively). The tool description adds no parameter information beyond what the schema already provides. According to the rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description '查询可用的命令列表' (Query available command list) clearly states the tool's purpose with a specific verb ('查询' - query) and resource ('可用的命令列表' - available command list). It distinguishes from the sibling 'executeCommand' (which executes commands rather than listing them) and 'help' (which likely provides documentation rather than listing). However, it doesn't explicitly differentiate from 'help' which might overlap in functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 doesn't mention when to use 'queryCommands' versus 'executeCommand' or 'help', nor does it specify any prerequisites or contexts where this tool is particularly appropriate. The user must infer usage from the tool name alone.

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. 3 tool updatesv1.0.0
    • First observedexecuteCommand
    • First observedhelp
    • First observedqueryCommands
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.7/5.0
Disambiguation5/5

The three tools have clearly distinct purposes: executeCommand performs actions, help provides documentation, and queryCommands lists available commands. There is no overlap in functionality, making it easy for an agent to select the correct tool for each task.

Naming Consistency4/5

The tool names follow a consistent verb_noun pattern (executeCommand, queryCommands) with one minor deviation (help is a noun-only name). This small inconsistency does not significantly impact readability or predictability, as the naming is still clear and logical.

Tool Count3/5

With only 3 tools, the server feels thin for a note-taking domain, as it lacks operations for creating, reading, updating, or deleting notes directly. While the tools provide a command-based interface, the count is borderline low for the apparent scope of managing notes in SiYuan.

Completeness2/5

The tool surface is significantly incomplete for a note-taking server. There are no tools for core CRUD operations on notes (e.g., create_note, get_note, update_note, delete_note), which are essential for agent workflows. The current tools only support command execution and help, leaving major gaps in functionality.

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

Related MCP Servers

Appeared in Searches

Latest Blog Posts

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/onigeya/siyuan-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server