List public classes exposed by the td module.
AI agents call get_td_classes to retrieve information from Touchdesigner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about the TouchDesigner API by listing available classes. It is a read-only operation with no side effects, no data modification, and no execution of user-supplied code. The blast radius is minimal—an agent can only learn what classes exist, which poses no security risk on its own.
From the tool's definition Tool name 'get_td_classes' and description 'List public classes exposed by the `td` module' indicate a query/introspection operation that retrieves information about available classes without modifying state or executing arbitrary code.
Attacks that exploit this kind of access
List public classes exposed by the td module. It is categorised as a Read tool in the Touchdesigner MCP Server, which means it retrieves data without modifying state.
Register the Touchdesigner MCP server in PolicyLayer and add a rule for get_td_classes: 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.
get_td_classes 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 get_td_classes 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 get_td_classes. 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.
get_td_classes 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 →