Apply targeted patches to a note using one unified batch schema. WORKFLOW: 1) Call get_note to obtain current content and contentHash (blobId), 2) Design patches, 3) Call patch_note with expectedHash. Use mode=
AI agents use patch_note to create or update resources in TriliumNext Notes' MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TriliumNext Notes' MCP Server environment.
The patch_note tool modifies note content, which is a reversible Write operation. While the description is truncated (ending with 'Use mode='), the clear intent is to apply patches that change note state. It is not Destructive because patches are typically additive/modifying rather than deletion, not Execute because it doesn't run arbitrary code, and not Financial.
From the tool's definition Tool description states it 'Apply[s] targeted patches to a note' and workflow involves calling patch_note to modify content. The context of a notes application indicates this modifies existing data reversibly.
Documented attack patterns abuse exactly the kind of access patch_note gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TriliumNext Notes' MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for patch_note:
{
"version": "1",
"default": "deny",
"tools": {
"patch_note": {
"limits": [
{
"counter": "patch_note_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}patch_note stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Apply targeted patches to a note using one unified batch schema. WORKFLOW: 1) Call get_note to obtain current content and contentHash (blobId), 2) Design patches, 3) Call patch_note with expectedHash. Use mode=. It is categorised as a Write tool in the TriliumNext Notes' MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TriliumNext Notes' MCP Server MCP server in PolicyLayer and add a rule for patch_note: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches TriliumNext Notes' MCP Server. Nothing to install.
patch_note is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the patch_note rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for patch_note. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
patch_note is provided by the TriliumNext Notes' MCP Server MCP server (tan-yong-sheng/triliumnext-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 TriliumNext Notes' MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 TriliumNext Notes' MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.