Get Ghost site information (title, URL, version).
AI agents call ghost_site_info to retrieve information from Ghost CMS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns Ghost site metadata. It performs no writes, deletions, or side effects. The blast radius of misuse is minimal—an attacker gains only publicly-available site information. This is the lowest-risk classification.
From the tool's definition Tool retrieves site information (title, URL, version) without modifying any data. The verb 'get' and the read-only nature of site metadata information confirm this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get Ghost site information (title, URL, version). It is categorised as a Read tool in the Ghost CMS MCP MCP Server, which means it retrieves data without modifying state.
Register the Ghost CMS MCP server in PolicyLayer and add a rule for ghost_site_info: 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_site_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ghost_site_info 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_site_info. 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_site_info 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 →