Add a note to the ideas or learning section
AI agents use addNote to create or update resources in Knowledge MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Knowledge MCP Server environment.
This tool creates new note entries in a GitHub-backed knowledge base. It is reversible (notes can be edited or deleted), has no destructive semantics, does not execute arbitrary code, and poses minimal risk. The blast radius is limited to the user's own knowledge repository with no side effects beyond the note creation itself.
From the tool's definition Tool name is 'addNote' and description states 'Add a note to the ideas or learning section' — the verb 'Add' and the context of appending to a markdown-based knowledge repository indicate data creation/modification.
Attacks that exploit this kind of access
Add a note to the ideas or learning section. It is categorised as a Write tool in the Knowledge MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Knowledge MCP Server MCP server in PolicyLayer and add a rule for addNote: 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 MCP Server. Nothing to install.
addNote 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 addNote 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 addNote. 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.
addNote is provided by the Knowledge MCP Server MCP server (vuluu2k/knowledge_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 →