記事を更新
AI agents use update_post to create or update resources in Ghost MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghost MCP Server environment.
This tool modifies existing post content reversibly within a CMS system. It is classified as Write rather than Execute because it operates on a specific data entity (posts) via a dedicated endpoint, not arbitrary code execution. It is not Destructive because updates are reversible (old versions typically remain in CMS history).
From the tool's definition Tool name 'update_post' combined with server description stating it 'allow[s] programmatic management of Ghost CMS features, including posts' and context of sibling tools (create_post, delete_post) that perform destructive/write operations on posts.
Attacks that exploit this kind of access
記事を更新. It is categorised as a Write tool in the Ghost MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ghost MCP Server MCP server in PolicyLayer and add a rule for 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 MCP Server. Nothing to install.
update_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 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.
Set action: deny in the PolicyLayer policy for 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.
update_post is provided by the Ghost MCP Server MCP server (mtane0412/ghost-mcp-server). 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 →