AI agents call x_get_followers to retrieve information from X without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves follower data for a user. It performs no mutations, does not execute code or commands, does not delete data, and does not involve financial transactions. It is a straightforward read operation similar to a search or fetch. The blast radius of misuse is minimal—an agent could only over-retrieve publicly available follower lists, which poses no destructive or security risk.
From the tool's definition Tool name 'x_get_followers' and description 'Get a user's followers' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get a user's followers. It is categorised as a Read tool in the X MCP Server, which means it retrieves data without modifying state.
Register the X MCP server in PolicyLayer and add a rule for x_get_followers: 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 X. Nothing to install.
x_get_followers 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 x_get_followers 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 x_get_followers. 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.
x_get_followers is provided by the X MCP server (mindmadelab/x-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 →