医療AI関連の学術記事を生成します(LLMO対策、サムネイル指示付き)
AI agents use miyabi__generate_article to create or update resources in Enhanced Miyabi MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Enhanced Miyabi MCP Server environment.
This tool creates or modifies content (generating academic articles) reversibly—articles can be edited, deleted, or regenerated. It does not execute arbitrary code, delete data irreversibly, or move money. While it generates text output, the act of generation itself is a Write operation.
From the tool's definition Tool name 'miyabi__generate_article' and description indicating article generation ("学術記事を生成します" = "generates academic articles").
Attacks that exploit this kind of access
医療AI関連の学術記事を生成します(LLMO対策、サムネイル指示付き). It is categorised as a Write tool in the Enhanced Miyabi MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Enhanced Miyabi MCP Server MCP server in PolicyLayer and add a rule for miyabi__generate_article: 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 Enhanced Miyabi MCP Server. Nothing to install.
miyabi__generate_article is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the miyabi__generate_article 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 miyabi__generate_article. 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.
miyabi__generate_article is provided by the Enhanced Miyabi MCP Server MCP server (mo666-med/enhanced-miyabi-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 →