カクヨムで作品を検索
AI agents call search_works to retrieve information from Kakuyomu MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches for works on a Japanese novel publishing platform. Search operations are inherently read-only—they query and retrieve information without creating, modifying, deleting, or executing code. The blast radius of misuse is minimal; an agent could only retrieve unwanted search results, not cause side effects.
From the tool's definition Tool name 'search_works' and description 'カクヨムで作品を検索' (search works on Kakuyomu) indicates a search operation that retrieves data without modification.
Attacks that exploit this kind of access
カクヨムで作品を検索. It is categorised as a Read tool in the Kakuyomu MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kakuyomu MCP Server MCP server in PolicyLayer and add a rule for search_works: 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 Kakuyomu MCP Server. Nothing to install.
search_works 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 search_works 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 search_works. 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.
search_works is provided by the Kakuyomu MCP Server MCP server (106-/kakuyomu-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_works is one line of Kakuyomu MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →