AI agents use append_to_daily_note to create or update resources in Obsidian — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obsidian environment.
This tool appends content to an existing note, which is a reversible write operation. It modifies a file in the Obsidian vault by adding data, but does not delete or overwrite existing content. Misuse could result in unwanted content being added to daily notes, but the operation is reversible by removing the appended text.
From the tool's definition Append markdown to the current daily (or weekly/etc.) note. Common pattern: agent logs what it just did at the end of the day.
Attacks that exploit this kind of access
Append markdown to the current daily (or weekly/etc.) note. Common pattern: agent logs what it just did at the end of the day. It is categorised as a Write tool in the Obsidian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obsidian MCP server in PolicyLayer and add a rule for append_to_daily_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 Obsidian. Nothing to install.
append_to_daily_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 append_to_daily_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 append_to_daily_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.
append_to_daily_note is provided by the Obsidian MCP server (yanxue06/obsidian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →