AI agents call roles_read to retrieve information from Ghost MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves role information from Ghost CMS without modifying, deleting, or executing operations. The '_read' suffix and positioning among other data management tools strongly indicate a simple query/retrieval function. The empty description lowers confidence slightly, but the naming convention and server architecture provide sufficient evidence for a Read classification with low severity.
From the tool's definition Tool name 'roles_read' indicates a read-only operation; sibling tools follow a clear pattern where '_read' variants (members_read, roles_read) perform data retrieval, while '_add', '_delete', '_edit' perform modifications.
Documented attack patterns abuse exactly the kind of access roles_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ghost MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for roles_read:
{
"version": "1",
"default": "deny",
"tools": {
"roles_read": {}
}
}roles_read is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
roles_read. It is categorised as a Read tool in the Ghost MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Ghost MCP Server MCP server in PolicyLayer and add a rule for roles_read: 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.
roles_read 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 roles_read 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 roles_read. 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.
roles_read is provided by the Ghost MCP Server MCP server (mfydev/ghost-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ghost MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
42 Ghost MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.