Return errors and warnings at path.
AI agents call get_errors 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 queries error and warning messages from a specified path in TouchDesigner. It is a read-only operation that retrieves existing information with no side effects, no data modification, and no code execution. The retrieval of diagnostic/logging information poses minimal risk even in an adversarial context, as errors and warnings are typically non-sensitive operational data.
From the tool's definition 'Return errors and warnings at `path`' - the tool retrieves diagnostic information without modifying state or executing code.
Attacks that exploit this kind of access
Return errors and warnings at path. 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_errors: 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_errors 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_errors 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_errors. 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_errors 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 →