AI agents call get_followers to retrieve information from LineWhiz without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns follower data without modifying, deleting, or executing any operations. It is a simple data retrieval function that fits the 'Read' category. Severity is low because while user ID lists could have privacy implications, the tool itself performs no destructive or harmful action and the data accessed is limited to followers who have already opted-in to the account.
From the tool's definition Tool name is 'get_followers' and description states 'Get the list of user IDs of followers of this LINE OA' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the list of user IDs of followers of this LINE OA. It is categorised as a Read tool in the LineWhiz MCP Server, which means it retrieves data without modifying state.
Register the LineWhiz MCP server in PolicyLayer and add a rule for 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 LineWhiz. Nothing to install.
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 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 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.
get_followers is provided by the LineWhiz MCP server (kinzen-dev/linewhiz). 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 →