Search blog posts by keyword
AI agents call search_blog to retrieve information from Hatena Blog 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 or queries data (blog posts) based on search terms without any side effects. It matches the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch)'. The search operation is non-destructive, read-only, and carries minimal security risk even if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Search blog posts by keyword' with no modification, deletion, or execution capability. Server description confirms it 'Enables searching and retrieving articles' which are read-only operations.
Attacks that exploit this kind of access
Search blog posts by keyword. It is categorised as a Read tool in the Hatena Blog MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hatena Blog MCP Server MCP server in PolicyLayer and add a rule for search_blog: 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 Hatena Blog MCP Server. Nothing to install.
search_blog 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_blog 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_blog. 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_blog is provided by the Hatena Blog MCP Server MCP server (serima/hatena-blog-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 →