AI agents use article_publish to create or update resources in Voog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Voog environment.
Publishing an article in a CMS creates or modifies data reversibly—the published state can be reverted by unpublishing. This is a Write operation rather than Execute because it performs a specific CMS operation (state transition) rather than arbitrary code execution.
From the tool's definition Tool description indicates 'Publish an article' which modifies article status from draft/unpublished to published state. The incomplete description mentions autosave copying behavior suggesting state transitions in a CMS context.
Attacks that exploit this kind of access
Publish an article. Voog only copies autosaved_* →. It is categorised as a Write tool in the Voog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Voog MCP server in PolicyLayer and add a rule for article_publish: 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 Voog. Nothing to install.
article_publish 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 article_publish 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 article_publish. 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.
article_publish is provided by the Voog MCP server (runnel/voog-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 →