AI agents call obtener_info_sitio to retrieve information from Moodle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration and authentication metadata without modifying, executing code, or affecting data. The explicit mention of verifying 'which plugin WS functions are exposed' indicates an informational/discovery purpose. No side effects or state changes occur.
From the tool's definition Tool is named 'obtener_info_sitio' (get site info) and described as 'Get site + user + token info'. The description explicitly references 'core_webservice_get_site_info', a standard Moodle read-only API call that retrieves metadata about the site, user, and…
Attacks that exploit this kind of access
Get site + user + token info (core_webservice_get_site_info). Use include_functions=true at bootstrap to verify which plugin WS functions are exposed to the token. It is categorised as a Read tool in the Moodle MCP Server, which means it retrieves data without modifying state.
Register the Moodle MCP server in PolicyLayer and add a rule for obtener_info_sitio: 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 Moodle. Nothing to install.
obtener_info_sitio 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 obtener_info_sitio 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 obtener_info_sitio. 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.
obtener_info_sitio is provided by the Moodle MCP server (marcosnahuel/moodle-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 →