Write a note under vault/01_Notes by type. Does not write vault/04_Knowledge.
AI agents use note_write to create or update resources in Knowledge Wiki — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Knowledge Wiki environment.
This tool creates or modifies notes in the Obsidian vault (vault/01_Notes), which is a reversible action. It does not delete data (thus not Destructive), does not execute arbitrary code (thus not Execute), and does not involve financial transactions (thus not Financial).
From the tool's definition Tool description explicitly states 'Write a note' and 'note_write' as the function name, indicating creation or modification of note content in the vault.
Attacks that exploit this kind of access
Write a note under vault/01_Notes by type. Does not write vault/04_Knowledge. It is categorised as a Write tool in the Knowledge Wiki MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Knowledge Wiki MCP server in PolicyLayer and add a rule for note_write: 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 Knowledge Wiki. Nothing to install.
note_write 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 note_write 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 note_write. 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.
note_write is provided by the Knowledge Wiki MCP server (pongs1/knowledge-wiki-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 →