AI agents use create_note to create or update resources in Leetcode — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Leetcode environment.
This tool creates new personal notes associated with LeetCode problems. It is Write category because it creates/adds data (a note) that can be modified or deleted later without permanent system damage. The severity is low because notes are non-critical metadata with minimal blast radius if an AI agent creates unwanted notes - they can be easily deleted by the user.
From the tool's definition Tool name is 'create_note' and description states it 'Creates a new note' which adds new data to the user's account. The description explicitly indicates this 'allows users to save personal comments and observations' - reversible data creation.
Attacks that exploit this kind of access
Creates a new note for a specific LeetCode problem, allowing users to save personal comments and observations for future reference (requires authentication, CN only). It is categorised as a Write tool in the Leetcode MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Leetcode MCP server in PolicyLayer and add a rule for create_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 Leetcode. Nothing to install.
create_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 create_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 create_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.
create_note is provided by the Leetcode MCP server (@jinzcdev/leetcode-mcp-server). 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 →