Get all users
AI agents call get_users to retrieve information from FakeStore MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves all users from the system, making it a Read operation. However, severity is high rather than low because: (1) user data typically contains sensitive personally identifiable information (PII) such as names, email addresses, phone numbers, and account details; (2) bulk retrieval of all users ('get_all' semantics) creates a large blast radius if misused by an AI agent to exfiltrate the entire user…
From the tool's definition Tool name 'get_users' with description 'Get all users' retrieves user data without modification. The action is explicitly a retrieval operation ('Get'), which is characteristic of Read operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Get all users. It is categorised as a Read tool in the FakeStore MCP MCP Server, which means it retrieves data without modifying state.
Register the FakeStore MCP server in PolicyLayer and add a rule for get_users: 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 FakeStore MCP. Nothing to install.
get_users 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 get_users 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 get_users. 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.
get_users is provided by the FakeStore MCP server (mithgroth/fakestore-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 →