ghost_update_post · Ghost MCP: Risk & Policy

WHAT IT DOES

What ghost_update_post does on Ghost

AI agents use ghost_update_post 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.

WHY IT NEEDS A POLICY

Why ghost_update_post needs a policy

Updates to blog posts are reversible modifications (data can be restored from backups or previous versions), distinguishing this from Destructive category. The severity is high because an AI agent with this capability could maliciously modify published blog content at scale, affecting public-facing information and potentially damaging reputation or spreading misinformation.

From the tool's definition Tool description explicitly states "Update an existing Ghost post". The tool modifies blog post content reversibly (update operation), and the sibling context shows this is a Ghost blog management server with complementary create, delete, and publish…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ghost_update_post Rate-limited

ghost_update_post stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ghost_update_post": {
      "limits": [
        {
          "counter": "ghost_update_post_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ghost, so you can run agents against it safely.

FAQ

Questions about ghost_update_post

What does the ghost_update_post tool do? +

Update an existing Ghost post (fetches updated_at automatically for optimistic locking). 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.

How do I enforce a policy on ghost_update_post? +

Register the Ghost MCP server in PolicyLayer and add a rule for ghost_update_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. Nothing to install.

What risk level is ghost_update_post? +

ghost_update_post is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit ghost_update_post? +

Yes. Add a rate_limit block to the ghost_update_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.

How do I block ghost_update_post completely? +

Set action: deny in the PolicyLayer policy for ghost_update_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.

What MCP server provides ghost_update_post? +

ghost_update_post 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.