AI agents call get_activity_code to retrieve information from Smokeball without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a specific activity code record using an ID parameter. It performs a read-only query with no modification, deletion, or execution of external operations. The action is informational only, making it a Read category tool with low severity since accessing activity code metadata poses minimal risk to the Smokeball system.
From the tool's definition Tool name is 'get_activity_code' and description states 'Get an activity code by ID.' The verb 'get' and the retrieval-focused operation indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Get an activity code by ID. It is categorised as a Read tool in the Smokeball MCP Server, which means it retrieves data without modifying state.
Register the Smokeball MCP server in PolicyLayer and add a rule for get_activity_code: 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 Smokeball. Nothing to install.
get_activity_code 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_activity_code 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_activity_code. 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_activity_code is provided by the Smokeball MCP server (rosenadvertising/smokeball-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 →