Compare different releases of the same content
AI agents call compare-releases to retrieve information from Yarr Media Stack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents information about different releases for comparison purposes. It performs a read-only operation on media metadata without creating, modifying, deleting, or executing any actions. The comparison operation is a passive analysis of existing data, consistent with the 'Read' category (search, list, get, fetch).
From the tool's definition Tool name 'compare-releases' and description 'Compare different releases of the same content' indicate retrieval and comparison of existing data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Compare different releases of the same content. It is categorised as a Read tool in the Yarr Media Stack MCP Server, which means it retrieves data without modifying state.
Register the Yarr Media Stack MCP server in PolicyLayer and add a rule for compare-releases: 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 Yarr Media Stack. Nothing to install.
compare-releases 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 compare-releases 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 compare-releases. 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.
compare-releases is provided by the Yarr Media Stack MCP server (mcpnexus-registry/yarr). 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 →