Search for available releases for a TV series episode
AI agents call interactive_search to retrieve information from Sonarr MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries available releases without side effects. It does not create, modify, delete, or execute external operations. While the server as a whole includes destructive tools (delete_series) and execute-class tools (download_release), this specific tool is purely informational and read-only.
From the tool's definition Tool name is 'interactive_search' and description states 'Search for available releases for a TV series episode' — a query operation with no modification, deletion, or execution.
Attacks that exploit this kind of access
Search for available releases for a TV series episode. It is categorised as a Read tool in the Sonarr MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sonarr MCP Server MCP server in PolicyLayer and add a rule for interactive_search: 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 Sonarr MCP Server. Nothing to install.
interactive_search 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 interactive_search 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 interactive_search. 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.
interactive_search is provided by the Sonarr MCP Server MCP server (micky-devs/sonarr-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 →