Publish a draft post.
AI agents use ghost_publish_post to create or update resources in Ghost CMS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghost CMS MCP environment.
Publishing a post changes its visibility and status in the CMS, making it live and accessible to readers. This is a reversible modification (can be unpublished/drafted again) rather than data deletion or destruction. While it has organizational/reputational consequences if misused by an agent, it does not permanently destroy data, execute arbitrary code, or move money.
From the tool's definition Tool name and description indicate 'Publish a draft post' — this transitions a post from draft status to published status, modifying its state in the CMS.
Attacks that exploit this kind of access
Publish a draft post. It is categorised as a Write tool in the Ghost CMS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ghost CMS MCP server in PolicyLayer and add a rule for ghost_publish_post: 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 Ghost CMS MCP. Nothing to install.
ghost_publish_post 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 ghost_publish_post 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 ghost_publish_post. 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.
ghost_publish_post is provided by the Ghost CMS MCP server (matveev-pavel/ghost-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 →