Search classical Japanese texts with advanced normalization options
AI agents call genji_search to retrieve information from Genji 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 and queries classical Japanese literature texts from the Genji API without any side effects. It performs analysis through normalization options but does not create, modify, delete, or execute external operations. The search function is read-only access to a literature database, making it a clear Read category tool with low severity risk.
From the tool's definition Tool name 'genji_search' and description 'Search classical Japanese texts with advanced normalization options' indicate a search operation.
Attacks that exploit this kind of access
Search classical Japanese texts with advanced normalization options. It is categorised as a Read tool in the Genji MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Genji MCP Server MCP server in PolicyLayer and add a rule for genji_search: 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 Genji MCP Server. Nothing to install.
genji_search 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 genji_search 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 genji_search. 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.
genji_search is provided by the Genji MCP Server MCP server (nakamura196/genji-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 →