AI agents use generate_article to create or update resources in Outrank — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outrank environment.
The tool creates new content (SEO articles) and can automatically publish it to a CMS, making it a Write operation. It reaches 'high' severity because uncontrolled article generation and auto-publishing could flood a CMS with unwanted content or overwrite existing material. The 'optional' nature of auto-publish and the creation (rather than deletion) of content places this in Write rather than Destructive.
From the tool's definition Tool description states it can 'Generate a long-form SEO article' and includes 'optional auto-publish to the connected CMS', indicating creation and modification of content in an external system.
Attacks that exploit this kind of access
Generate a long-form SEO article targeted at a specific keyword, with optional auto-publish to the connected CMS. It is categorised as a Write tool in the Outrank MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Outrank MCP server in PolicyLayer and add a rule for 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 Outrank. Nothing to install.
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 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 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.
generate_article is provided by the Outrank MCP server (nobanks/outrank-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 →