AI agents call cf_accounts to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries Cloudflare accounts. However, the severity is elevated to 'medium' rather than 'low' because: (1) it operates within a credential management system ('Self-hosted credential store and API proxy') with centralized access control, (2) the results enumerate all accessible accounts, providing reconnaissance data that could facilitate lateral movement across Cloudflare…
From the tool's definition Tool name 'cf_accounts' and description 'List all Cloudflare accounts accessible with the configured API token' indicates a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List all Cloudflare accounts accessible with the configured API token. Use this first to get account IDs needed by cf_tunnels, cf_tunnel_config, and cf_workers. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for cf_accounts: 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 Access. Nothing to install.
cf_accounts 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 cf_accounts 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 cf_accounts. 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.
cf_accounts is provided by the Access MCP server (scottpedia0/access). 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 →