AI agents use tdarr_create_plugin to create or update resources in Tdarr — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tdarr environment.
This tool creates a new plugin, which is a reversible modification to the system's plugin library. While plugin creation could enable code execution if the created plugin is later applied to transcoding workflows, the tool itself only creates/writes the plugin definition—it does not execute it.
From the tool's definition Tool name 'tdarr_create_plugin' and description 'Create a basic classic plugin using the classic plugin creator' indicate a write operation that creates a new plugin artifact.
Attacks that exploit this kind of access
Create a basic classic plugin using the classic plugin creator. It is categorised as a Write tool in the Tdarr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tdarr MCP server in PolicyLayer and add a rule for tdarr_create_plugin: 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 Tdarr. Nothing to install.
tdarr_create_plugin is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the tdarr_create_plugin 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 tdarr_create_plugin. 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.
tdarr_create_plugin is provided by the Tdarr MCP server (maximeallanic/tdarr-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 →