AI agents call check_caps_compatible 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 performs a read-only compatibility check on GStreamer capability specifications. It takes two caps as input and returns whether they can intersect, with no side effects, data modification, code execution, or resource consumption. The operation is purely informational, analogous to a comparison or validation query.
From the tool's definition Tool description: 'Check if two GStreamer caps can intersect (are compatible)' — a query operation that tests capability compatibility without modifying state or executing code.
Attacks that exploit this kind of access
Check if two GStreamer caps can intersect (are compatible). 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 check_caps_compatible: 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.
check_caps_compatible 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 check_caps_compatible 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 check_caps_compatible. 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.
check_caps_compatible 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 →