profile_cook_cost
Read-only: sample cook times over a window (N samples × intervalMs) and rank hotspot nodes by p95 cook time. Use this to diagnose intermittent stalls that a single get_td_performance snapshot misses. Returns {path, samples, intervalMs, targetFps, frameBudgetMs, windowMs, hotspots[], warnings[]}.
This record as markdown: /tools/io-github-pantani-tdmcp/profile-cook-cost.md
What profile_cook_cost does on tdmcp — TouchDesigner MCP server
AI agents call profile_cook_cost to retrieve information from tdmcp — TouchDesigner MCP server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why profile_cook_cost is rated Low
This tool only samples and reads performance metrics from TouchDesigner without modifying any state, parameters, or data. It explicitly declares itself as 'read-only' and its sole purpose is diagnostic analysis of cooking/rendering performance. There are no side effects, modifications, code execution, or irreversible operations. The returned data structure confirms it is purely observational.
From the tool's definition Read-only: sample cook times over a window (N samples × intervalMs) and rank hotspot nodes by p95 cook time. Use this to diagnose intermittent stalls... Returns {path, samples, intervalMs, targetFps, frameBudgetMs, windowMs, hotspots[], warnings[]}
Attacks that exploit this kind of access
The rule that runs profile_cook_cost safely
PolicyLayer is an MCP gateway: it sits between your AI agents and tdmcp — TouchDesigner MCP server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For profile_cook_cost, this is the rule to start with:
profile_cook_cost is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect tdmcp — TouchDesigner MCP server, apply this rule, and every profile_cook_cost call is checked against it from then on.
Questions about profile_cook_cost
Read-only: sample cook times over a window (N samples × intervalMs) and rank hotspot nodes by p95 cook time. Use this to diagnose intermittent stalls that a single get_td_performance snapshot misses. Returns {path, samples, intervalMs, targetFps, frameBudgetMs, windowMs, hotspots[], warnings[]}. It is categorised as a Read tool in the tdmcp — TouchDesigner MCP server MCP Server, which means it retrieves data without modifying state.
Register the tdmcp — TouchDesigner MCP server MCP server in PolicyLayer and add a rule for profile_cook_cost: 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 tdmcp — TouchDesigner MCP server. Nothing to install.
profile_cook_cost 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 profile_cook_cost 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 profile_cook_cost. 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.
profile_cook_cost is provided by the tdmcp — TouchDesigner MCP server MCP server (@dpantani/tdmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on tdmcp — TouchDesigner MCP server, and thousands of servers like it.
This server
Across the catalogue