Get a direct stream URL for a Jellyfin item. Use for playback or sharing.
AI agents call crow_jellyfin_play to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a stream URL without creating, modifying, deleting, or executing operations on the Jellyfin system. It is purely informational—returning a URL for accessing media content. The blast radius of misuse is minimal: an agent could potentially share a stream URL with unauthorized parties, but this is a read-only disclosure risk rather than a write, execute, destructive, or financial risk.
From the tool's definition Tool description states 'Get a direct stream URL for a Jellyfin item. Use for playback or sharing.' The verb 'get' and the stated purposes of retrieval for playback or sharing indicate data retrieval with no modification or deletion of underlying data.
Documented attack patterns abuse exactly the kind of access crow_jellyfin_play gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_jellyfin_play:
{
"version": "1",
"default": "deny",
"tools": {
"crow_jellyfin_play": {}
}
} crow_jellyfin_play is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a direct stream URL for a Jellyfin item. Use for playback or sharing. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crow_jellyfin_play: 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 Crow. Nothing to install.
crow_jellyfin_play 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 crow_jellyfin_play 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 crow_jellyfin_play. 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.
crow_jellyfin_play is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.