Disconnect whatever feeds input input_index on path.
AI agents use disconnect_input to create or update resources in Touchdesigner — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Touchdesigner environment.
This tool modifies the state of TouchDesigner's operator graph by disconnecting inputs, which is a reversible change (can be reconnected via 'connect_operators'). It does not delete operators (would be Destructive), execute arbitrary code (Execute category), or permanently destroy data.
From the tool's definition Tool name 'disconnect_input' and description 'Disconnect whatever feeds input' indicates modification of operator connections in TouchDesigner's node graph.
Attacks that exploit this kind of access
Disconnect whatever feeds input input_index on path. It is categorised as a Write tool in the Touchdesigner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Touchdesigner MCP server in PolicyLayer and add a rule for disconnect_input: 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 Touchdesigner. Nothing to install.
disconnect_input 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 disconnect_input 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 disconnect_input. 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.
disconnect_input is provided by the Touchdesigner MCP server (mrinalghosh/touchdesigner-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 →