TriliumNext (trilium-mcp)
Read and write a self-hosted TriliumNext knowledge base over its ETAPI.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
{
"mcpServers": {
"trilium-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/ovden13/trilium-mcp:0.1.5"
],
"env": {
"TRILIUM_URL": "<trilium_url>",
"TRILIUM_TOKEN": "<your-trilium_token>",
"TRILIUM_HTTP_TIMEOUT_SECONDS": "<trilium_http_timeout_seconds>",
"TRILIUM_MCP_LOG": "<trilium_mcp_log>"
}
}
}
}TRILIUM_URLBase URL of the Trilium ETAPI. Comma-separated for failover: fast LAN first, public fallback (e.g. http://192.168.0.10:8092,https://memo.example.com).
TRILIUM_TOKENETAPI token created in Trilium under Options -> ETAPI
TRILIUM_HTTP_TIMEOUT_SECONDSPer-request HTTP timeout in seconds (default 30)
TRILIUM_MCP_LOGTool-call log level on stderr: off / info (default) / debug
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
Expert-curated knowledge graphs for AI agents — PSFK Retail, Beauty, Sports and more.