List all sites in your Plausible account
AI agents call list_sites to retrieve information from Plausible MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/lists data from the Plausible account without creating, modifying, deleting, or executing any operations. It is a straightforward Read operation with low severity since listing sites exposes account structure but not sensitive traffic data itself. The low blast radius reflects that an AI agent misusing this tool could only enumerate which sites exist in the account.
From the tool's definition Tool name 'list_sites' and description 'List all sites in your Plausible account' indicate a retrieval operation that queries and returns data about existing sites with no modification or side effects.
Attacks that exploit this kind of access
List all sites in your Plausible account. It is categorised as a Read tool in the Plausible MCP MCP Server, which means it retrieves data without modifying state.
Register the Plausible MCP server in PolicyLayer and add a rule for list_sites: 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 Plausible MCP. Nothing to install.
list_sites 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 list_sites 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 list_sites. 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.
list_sites is provided by the Plausible MCP server (the-focus-ai/plausible-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 →