What dependencies or runtime are required?
Node.js >= 23.10.0 and pnpm are required for local builds. A Docker image is also provided.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"onigeya_siyuan-mcp-server": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"\\"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
SiYuan Note MCP Server is an MCP server implementation that integrates with the SiYuan Note system, enabling AI models to access and manipulate note data. It provides a command‑based interface for notebooks, documents, blocks, files, assets, SQL queries, attributes, exports, and system functions.
Configure a SIYUAN_TOKEN environment variable with the SiYuan API token (found in SiYuan Note Settings > About). Add the server to Claude Desktop’s claude_desktop_config.json using npx -y @onigeya/siyuan-mcp-server, or run locally with pnpm start after installing dependencies. A Docker image is also available.
Node.js >= 23.10.0 and pnpm are required for local builds. A Docker image is also provided.
The server requires a `SIYUAN_TOKEN` environment variable, which is the API token from SiYuan Note. It is used for API authentication.
The README does not specify transport details; it is an MCP server (presumably stdio for Claude Desktop) but no explicit transport is mentioned.
Yes, it provides `query.sql` and `sql.sql` commands to execute SQL queries against the SiYuan note database.
Data is stored within the SiYuan Note system; the server accesses it via SiYuan’s API. No data is stored by the server itself.

The official Semantic-UI-React integration
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
Comments