内容ベース検索を実行します
AI agents call perform_content_search to retrieve information from Claude MCP Server Integration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data based on content without creating, modifying, or deleting anything. It is a classic Read operation. The Japanese description translates to 'performs content-based search,' confirming the read-only nature. No destructive, financial, or code execution capabilities are implied.
From the tool's definition Tool name 'perform_content_search' and description '内容ベース検索を実行します' (performs content-based search) indicate a query/search operation with no side effects.
Attacks that exploit this kind of access
内容ベース検索を実行します. It is categorised as a Read tool in the Claude MCP Server Integration MCP Server, which means it retrieves data without modifying state.
Register the Claude MCP Server Integration MCP server in PolicyLayer and add a rule for perform_content_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 Claude MCP Server Integration. Nothing to install.
perform_content_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 perform_content_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 perform_content_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.
perform_content_search is provided by the Claude MCP Server Integration MCP server (mokemoke0821/claude-mcp-integration). 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 →