Get problematic items that need extra practice
AI agents call get_leeches to retrieve information from WaniKani MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data about the user's problematic WaniKani items ('leeches' are items that users struggle with). It performs no side effects—no data is created, modified, deleted, or executed. This is a straightforward Read operation that queries existing learning progress information to support personalized learning recommendations.
From the tool's definition Tool name 'get_leeches' and description 'Get problematic items that need extra practice' indicate data retrieval with no modification.
Attacks that exploit this kind of access
Get problematic items that need extra practice. It is categorised as a Read tool in the WaniKani MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WaniKani MCP Server MCP server in PolicyLayer and add a rule for get_leeches: 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 WaniKani MCP Server. Nothing to install.
get_leeches is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_leeches 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 get_leeches. 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.
get_leeches is provided by the WaniKani MCP Server MCP server (jackedney/wanikani-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 →