Search for movies and TV shows by title, genre, year, rating, or quality. Returns matching content with metadata (title, year, genres, IMDb/TMDB ratings) and torrent download options (magnet links, quality, seeders, file size). This is the primary tool — use it first when a user asks to find, dow...
AI agents call search_content to retrieve information from TorrentClaw-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval and querying — characteristics of a Read operation. Although the results include magnet links to torrent content (which could facilitate copyright infringement), the tool's direct function is searching and returning metadata, not executing downloads or destructive operations.
From the tool's definition Tool description states it 'Search[es] for movies and TV shows' and 'Returns matching content with metadata' — core retrieval operations.
Attacks that exploit this kind of access
Search for movies and TV shows by title, genre, year, rating, or quality. Returns matching content with metadata (title, year, genres, IMDb/TMDB ratings) and torrent download options (magnet links, quality, seeders, file size). This is the primary tool — use it first when a user asks to find, download, or learn about a movie or TV show. Results include a content_id needed by get_watch_providers and get_credits. For TV shows, you can filter by season/episode. Season/episode can also be auto-detected from the query (e.g. It is categorised as a Read tool in the TorrentClaw-MCP MCP Server, which means it retrieves data without modifying state.
Register the TorrentClaw- MCP server in PolicyLayer and add a rule for search_content: 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 TorrentClaw-MCP. Nothing to install.
search_content 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 search_content 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 search_content. 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.
search_content is provided by the TorrentClaw- MCP server (torrentclaw/torrentclaw-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 →