AI agents call get_user_following to retrieve information from Mixcloud without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves follow relationship data from a user profile. It performs a query operation that does not modify, execute operations, or delete any data. The action is purely informational and read-only, making it a Read category tool with low severity since it accesses non-sensitive public relationship data on a music platform.
From the tool's definition Tool name 'get_user_following' and description 'Get a list of users that a Mixcloud user is following' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get a list of users that a Mixcloud user is following. It is categorised as a Read tool in the Mixcloud MCP Server, which means it retrieves data without modifying state.
Register the Mixcloud MCP server in PolicyLayer and add a rule for get_user_following: 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 Mixcloud. Nothing to install.
get_user_following 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_user_following 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_user_following. 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_user_following is provided by the Mixcloud MCP server (nelsonra/mixcloud-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 →