AI agents call get_plugin 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 plugin information by identifier without creating, modifying, or deleting any data. It has no side effects and presents minimal security risk—a typical Read category operation. The context of a law firm practice management system (Smokeball) does not elevate the risk, as reading plugin metadata does not affect firm operations, contacts, or financial data.
From the tool's definition Tool name 'get_plugin' with description 'Get a plugin by ID' indicates a retrieval operation with no modification or side effects. The verb 'Get' and the pattern of querying by ID are characteristic of read-only data access.
Attacks that exploit this kind of access
Get a plugin 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_plugin: 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_plugin 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_plugin 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_plugin. 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_plugin 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 →