AI agents call list_plugins to retrieve information from Gst without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays metadata about installed GStreamer plugins. It performs no side effects, makes no modifications, executes no code, and presents only read-only information about the system's GStreamer environment. The blast radius of misuse is minimal—an AI agent could only enumerate plugins, not manipulate them or cause system harm.
From the tool's definition Tool name 'list_plugins' and description 'List all installed GStreamer plugins with version and description' indicate a query/retrieval operation that enumerates installed plugins without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List all installed GStreamer plugins with version and description. It is categorised as a Read tool in the Gst MCP Server, which means it retrieves data without modifying state.
Register the Gst MCP server in PolicyLayer and add a rule for list_plugins: 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 Gst. Nothing to install.
list_plugins 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 list_plugins 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 list_plugins. 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.
list_plugins is provided by the Gst MCP server (wizenink/gst-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 →