Lancer un épisode de série dans Kodi
AI agents invoke play_episode to trigger actions in Kodi MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool launches/starts playback of a TV episode in Kodi, which is an external operation that affects the state of the media center. It doesn't merely read data, nor does it delete or modify stored data. It falls under Execute as it triggers an external operation (media playback) on the Kodi system.
From the tool's definition 'Lancer un épisode de série dans Kodi' (Launch a TV series episode in Kodi) — triggers external media playback operation
Attacks that exploit this kind of access
Lancer un épisode de série dans Kodi. It is categorised as a Execute tool in the Kodi MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kodi MCP Server MCP server in PolicyLayer and add a rule for play_episode: 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 Kodi MCP Server. Nothing to install.
play_episode is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the play_episode 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 play_episode. 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.
play_episode is provided by the Kodi MCP Server MCP server (laheud/kodi-mcp-server). 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 →