SiYuan▌
by xgq18237
Integrate SiYuan with leading case note software like therapynotes com for easy note creation, editing, and organization
Integrates with SiYuan note-taking application to enable complete knowledge management operations including note creation, editing, searching, and organization through TypeScript-based API connectivity.
Both formats append explainx.ai attribution and the canonical URL for this MCP server listing.
best for
- / Knowledge workers using SiYuan for note-taking
- / Automating note management workflows
- / Integrating SiYuan with AI assistants
capabilities
- / Create and edit SiYuan notes
- / Search through knowledge base content
- / Organize notes and notebooks
- / Access SiYuan API functionality
- / Manage note metadata and attributes
what it does
Connects to your SiYuan note-taking application to manage notes programmatically. Enables complete knowledge base operations through API integration.
about
SiYuan is a community-built MCP server published by xgq18237 that provides AI assistants with tools and capabilities via the Model Context Protocol. Integrate SiYuan with leading case note software like therapynotes com for easy note creation, editing, and organization It is categorized under productivity.
how to install
You can install SiYuan in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
license
MIT
SiYuan is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
readme
思源笔记 MCP 服务器 / SiYuan MCP Server
<div align="center"> </div>English Version
A Model Context Protocol (MCP) server for SiYuan Note, providing complete SiYuan API functionality.
🚀 Quick Start
Using npx (Recommended)
# Run directly (local SiYuan)
npx -y siyuan-mcp@latest
# Set environment variables for local access
SIYUAN_HOST=127.0.0.1 SIYUAN_PORT=6806 SIYUAN_TOKEN=your-token npx -y siyuan-mcp@latest
# For remote SiYuan behind HTTPS reverse proxy
SIYUAN_URL=https://siyuan.example.com SIYUAN_TOKEN=your-token npx -y siyuan-mcp@latest
Using Docker
# Pull image
docker pull zhizhiqq/siyuan-mcp:latest
# Run container
docker run -d \
-e SIYUAN_HOST=127.0.0.1 \
-e SIYUAN_PORT=6806 \
-e SIYUAN_TOKEN=your-token \
--name siyuan-mcp-server \
zhizhiqq/siyuan-mcp:latest
Configure MCP Client
Cursor Configuration
- Open Cursor settings (Ctrl/Cmd + ,)
- Search for "MCP" or "Model Context Protocol"
- Click "Add Server" or "添加服务器"
- Configure server information:
{
"mcpServers": {
"siyuan-mcp": {
"command": "npx",
"args": ["-y", "siyuan-mcp@latest"],
"env": {
"SIYUAN_HOST": "127.0.0.1",
"SIYUAN_PORT": "6806",
"SIYUAN_TOKEN": "your-api-token-here"
}
}
}
}
Claude Desktop Configuration
- Open Claude Desktop settings
- Go to "Model Context Protocol" settings
- Add new MCP server:
{
"mcpServers": {
"siyuan-mcp": {
"command": "npx",
"args": ["-y", "siyuan-mcp@latest"],
"env": {
"SIYUAN_HOST": "127.0.0.1",
"SIYUAN_PORT": "6806",
"SIYUAN_TOKEN": "your-api-token-here"
}
}
}
}
Remote Access via HTTPS (Reverse Proxy)
If your SiYuan instance is behind a reverse proxy (e.g., Traefik, nginx) with HTTPS:
{
"mcpServers": {
"siyuan-mcp": {
"command": "npx",
"args": ["-y", "siyuan-mcp@latest"],
"env": {
"SIYUAN_URL": "https://siyuan.example.com",
"SIYUAN_TOKEN": "your-api-token-here"
}
}
}
}
Docker Configuration
If you use Docker to run the service, you can configure the client to connect to the Docker container:
Cursor Docker Configuration
{
"mcpServers": {
"siyuan-mcp": {
"command": "docker",
"args": ["run", "--rm", "-e", "SIYUAN_HOST=127.0.0.1", "-e", "SIYUAN_PORT=6806", "-e", "SIYUAN_TOKEN=your-api-token-here", "zhizhiqq/siyuan-mcp:latest"],
"env": {}
}
}
}
Claude Desktop Docker Configuration
{
"mcpServers": {
"siyuan-mcp": {
"command": "docker",
"args": ["run", "--rm", "-e", "SIYUAN_HOST=127.0.0.1", "-e", "SIYUAN_PORT=6806", "-e", "SIYUAN_TOKEN=your-api-token-here", "zhizhiqq/siyuan-mcp:latest"],
"env": {}
}
}
}
Note: When using Docker configuration, ensure Docker is installed and running.
🔧 Environment Variables
| Variable | Description | Default | Required |
|---|---|---|---|
SIYUAN_URL | Full URL for SiYuan (e.g., https://siyuan.example.com). If set, overrides HOST/PORT. | - | No |
SIYUAN_HOST | SiYuan server address | 127.0.0.1 | No |
SIYUAN_PORT | SiYuan server port | 6806 | No |
SIYUAN_TOKEN | API token | - | Yes |
Note: Use SIYUAN_URL when connecting to a SiYuan instance behind an HTTPS reverse proxy. When SIYUAN_URL is set, SIYUAN_HOST and SIYUAN_PORT are ignored.
📋 Common Issues
Q: What if the connection fails?
A: Please check the following steps:
- Ensure SiYuan Note is running
- Check if the API token is correct
- Confirm there are open notebooks in SiYuan Note
- Restart SiYuan Note and Cursor
Q: How to get the correct API token?
A:
- Open SiYuan Note
- Go to
Settings→About→API Token - Click
Generate Tokenor copy existing token - Ensure the token format is correct (usually a string of alphanumeric characters)
Q: Why use -y parameter with npx?
A: The -y parameter automatically confirms package installation without prompting for user input, which is essential for MCP client configurations where interactive prompts would cause connection failures.
Q: How to connect to SiYuan behind a reverse proxy with HTTPS?
A: Use the SIYUAN_URL environment variable instead of SIYUAN_HOST and SIYUAN_PORT:
SIYUAN_URL=https://siyuan.example.com SIYUAN_TOKEN=your-token npx -y siyuan-mcp@latest
🎯 Features
📚 Notebook Management
Notebooks are the basic organizational units of SiYuan Note, each containing multiple documents.
list_notebooks- List all notebooks, get notebook IDs and namesopen_notebook- Open specified notebook, activate workspaceclose_notebook- Close specified notebook, release resourcesrename_notebook- Rename notebook, update display namecreate_notebook- Create new notebook, support custom namesremove_notebook- Delete notebook, clean related dataget_notebook_conf- Get notebook configuration informationset_notebook_conf- Save notebook configuration, custom settings
📄 Document Management
Documents are specific content units in notebooks, supporting hierarchical structure and path management.
create_doc- Create new document in specified notebook, support Markdown contentrename_doc- Rename document, keep content unchangedrename_doc_by_id- Rename by document ID, precise operationremove_doc- Delete document, clean file systemremove_doc_by_id- Delete by document ID, precise operationmove_docs- Move documents to other locations or notebooksmove_docs_by_id- Move by document ID, precise operationget_hpath_by_path- Get human-readable path by pathget_hpath_by_id- Get human-readable path by IDget_path_by_id- Get storage path by IDget_ids_by_hpath- Get IDs by human-readable path
🧩 Block Operations
Blocks are the smallest content units in SiYuan Note, supporting flexible editing, reorganization, and referencing.
insert_block- Insert block, support specified position and data typeprepend_block- Insert prepend child block, add content at parent block beginningappend_block- Insert append child block, add content at parent block endupdate_block- Update block content, support Markdown and DOM formatsdelete_block- Delete block, clean related referencesmove_block- Move block to new position, support hierarchical adjustmentget_block_kramdown- Get block kramdown source code, for exportget_child_blocks- Get child block list, traverse block structurefold_block- Fold block, hide child contentunfold_block- Unfold block, show child contenttransfer_block_ref- Transfer block reference, maintain reference relationships
🏷️ Attribute Operations
Block attributes are used to store metadata and custom information, supporting key-value pair storage.
set_block_attrs- Set block attributes, support custom key-value pairsget_block_attrs- Get block attributes, read metadata information
🔍 Search and Query
Get data from SiYuan Note through SQL queries, supporting complex query conditions.
sql_query- Execute SQL queries, support all SQLite syntaxflush_transaction- Commit transactions, ensure data persistence
📁 File Operations
Manage files and directories in SiYuan Note workspace, support resource management.
get_file- Get file content, read file dataremove_file- Delete file, clean storage spacerename_file- Rename file, update file pathread_dir- List directory content, browse file structureput_file- Write file, create or update file content
📤 Export Functions
Export SiYuan Note content to various formats, support backup and sharing.
export_md_content- Export Markdown text, maintain formatexport_resources- Export files and directories, include resource files
📢 Notification Functions
Push messages and error prompts to users, provide operation feedback.
push_msg- Push messages, display success promptspush_err_msg- Push error messages, display error information
💻 System Information
Get SiYuan Note system status and runtime information, monitor system health.
get_version- Get SiYuan Note version informationget_current_time- Get system current timeget_boot_progress- Get boot progress, monitor boot statuscheck_siyuan_status- Check SiYuan Note status and API availabilityget_workspace_info- Get workspace and connection information
🎨 Template Functions
Use template system to create dynamic content, support variable substitution.
render_template- Render template files, support external templatesrender_sprig- Render Sprig templates, support inline template syntax
🔄 Conversion Functions
Use Pandoc for document format conversion, support multiple output formats.
pandoc_convert- Pandoc conversion, support multiple document formats
📎 Resource Files
Manage resource files in SiYuan Note, support batch upload.
upload_asset- Upload resource files, support batch operations
🔧 Core Features
🚀 High Performance
- Asynchronous Processing: All API calls use asynchronous processing for faster response
- Batch Operations: Support batch document movement and block operations for improved efficiency
- Transaction Management: Built-in transaction mechanism ensures data consistency
🛡️ Secure and Reliable
- Authentication: Support API token authentication to protect data security
- Error Handling: Comprehensive error handling mechanism provides detailed error information
- **Pa
FAQ
- What is the SiYuan MCP server?
- SiYuan is a Model Context Protocol (MCP) server profile on explainx.ai. MCP lets AI hosts (e.g. Claude Desktop, Cursor) call tools and resources through a standard interface; this page summarizes categories, install hints, and community ratings.
- How do MCP servers relate to agent skills?
- Skills are reusable instruction packages (often SKILL.md); MCP servers expose live capabilities. Teams frequently combine both—skills for workflows, MCP for APIs and data. See explainx.ai/skills and explainx.ai/mcp-servers for parallel directories.
- How are reviews shown for SiYuan?
- This profile displays 39 aggregated ratings (sample rows for discoverability plus signed-in user reviews). Average score is about 4.7 out of 5—verify behavior in your own environment before production use.
Use Cases▌
Extended AI Capabilities
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Context Enhancement
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Workflow Automation
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Implementation Guide▌
Prerequisites
- ›Claude Desktop 0.7.0+ or Cursor IDE with MCP support
- ›Basic understanding of MCP architecture and capabilities
- ›Access credentials for integrated services (if required)
- ›Willingness to experiment and iterate on configuration
Time Estimate
15-60 minutes depending on server complexity
Installation Steps
- 1.Install MCP server: npm install -g [package-name] or via GitHub
- 2.Add server configuration to ~/.claude/mcp.json
- 3.Provide required credentials and configuration
- 4.Restart Claude Desktop to load new server
- 5.Test basic functionality with simple prompts
- 6.Explore capabilities and experiment with use cases
- 7.Document successful patterns for reuse
Troubleshooting
- ⚠MCP server not loading: Check config syntax, verify installation
- ⚠Connection errors: Check network, firewall, credentials
- ⚠Feature not working: Read server docs, check required parameters
- ⚠Performance issues: Monitor resource usage, check for network latency
- ⚠Conflicts with other servers: Check port assignments, namespace collisions
Best Practices▌
✓ Do
- +Read server documentation thoroughly before setup
- +Start with simple use cases to validate functionality
- +Test in non-production environment first
- +Monitor resource usage and performance
- +Keep servers updated for bug fixes and new features
- +Document configuration for team members
- +Use environment variables for sensitive configuration
✗ Don't
- −Don't grant overly permissive access to MCP servers
- −Don't skip reading security considerations in docs
- −Don't expose sensitive data without proper controls
- −Don't run untrusted MCP servers without code review
- −Don't ignore error messages—investigate root cause
💡 Pro Tips
- ★Combine multiple MCP servers for powerful workflows
- ★Create custom MCP servers for your specific needs
- ★Share successful configurations with team
- ★Use MCP inspector for debugging
- ★Join MCP community for tips and troubleshooting
Technical Details▌
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
- Model Context Protocol (MCP)
- JSON-RPC 2.0
- stdio or HTTP transport
Compatibility
- Claude Desktop
- Cursor IDE
- Custom MCP clients
When to Use This▌
✓ Use When
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid When
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.
Integration▌
- →Tool composition: Chain multiple MCP tools in workflows
- →Context augmentation: Provide AI with relevant external data
- →Action delegation: Let AI execute tasks on external systems
- →Bidirectional sync: Keep AI context and external systems in sync
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
List & Promote Your MCP Server
Share your MCP server with the developer community
Ratings
4.7★★★★★39 reviews- ★★★★★Layla Martin· Dec 28, 2024
Strong directory entry: SiYuan surfaces stars and publisher context so we could sanity-check maintenance before adopting.
- ★★★★★Shikha Mishra· Dec 4, 2024
I recommend SiYuan for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
- ★★★★★Kaira Reddy· Dec 4, 2024
SiYuan has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
- ★★★★★Emma Chen· Dec 4, 2024
We evaluated SiYuan against two servers with overlapping tools; this profile had the clearer scope statement.
- ★★★★★Rahul Santra· Nov 23, 2024
According to our notes, SiYuan benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
- ★★★★★Layla Jackson· Nov 23, 2024
SiYuan is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
- ★★★★★Arya Ghosh· Nov 19, 2024
We wired SiYuan into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
- ★★★★★Pratham Ware· Oct 14, 2024
SiYuan is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
- ★★★★★Kiara Huang· Oct 14, 2024
According to our notes, SiYuan benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
- ★★★★★Arya Bhatia· Oct 10, 2024
SiYuan reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
showing 1-10 of 39