AI agents call get_plugin_url 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 URL resource without creating, modifying, deleting, or executing any operations. It is a simple query/fetch operation that returns a URL string for display purposes. The retrieval of a plugin URL has minimal security impact unless the URL itself leads to malicious content, which is outside the scope of this tool's direct functionality. This is a typical Read category operation.
From the tool's definition The tool 'get_plugin_url' retrieves a URL for plugin display via an embedded iframe. The verb 'get' and the action of 'request the launch URL' indicate a data retrieval operation with no side effects.
Attacks that exploit this kind of access
Request the launch URL for a plugin (for embedded iframe display). 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_url: 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_url 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_url 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_url. 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_url 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 →