AI agents use ghost_update_tag to create or update resources in Ghost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghost environment.
This tool creates or modifies data in a reversible manner. While it alters tag metadata in a Ghost blog, the changes can be undone by updating the tag again with previous values. It does not delete data (which would be Destructive) nor execute arbitrary code (Execute). The blast radius is medium because incorrect tag updates could affect blog organization and SEO, but the changes are recoverable and limited in scope.
From the tool's definition The tool 'ghost_update_tag' is described as 'Update an existing Ghost tag (name, slug, description, and/or visibility)' — it modifies existing data reversibly by changing tag properties.
Attacks that exploit this kind of access
Update an existing Ghost tag (name, slug, description, and/or visibility), identified by ID or current slug. It is categorised as a Write tool in the Ghost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ghost MCP server in PolicyLayer and add a rule for ghost_update_tag: 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. Nothing to install.
ghost_update_tag 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_update_tag 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_update_tag. 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_update_tag is provided by the Ghost MCP server (uppinote20/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 →