create_fluid_sim
Build a real-time 2D fluid/ink/dye simulation (stable-fluids style: semi-Lagrangian advection + Jacobi pressure solve + gradient-subtract projection + dye advection) as a stack of GLSL TOPs in feedback loops inside a new baseCOMP under
This record as markdown: /tools/io-github-pantani-tdmcp/create-fluid-sim.md
What create_fluid_sim does on tdmcp — TouchDesigner MCP server
AI agents use create_fluid_sim to create or update resources in tdmcp — TouchDesigner MCP server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your tdmcp — TouchDesigner MCP server environment.
Why create_fluid_sim is rated Medium
This tool creates new nodes and components in a TouchDesigner project (a baseCOMP containing GLSL TOPs), which is a reversible write/create operation. It does not delete data, execute arbitrary code outside the TD environment, or involve financial transactions. The severity is medium because it modifies the project structure and could affect an existing network if placed incorrectly, but the operation is reversible.
From the tool's definition Build a real-time 2D fluid/ink/dye simulation... as a stack of GLSL TOPs in feedback loops inside a new baseCOMP
Attacks that exploit this kind of access
The rule that runs create_fluid_sim 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 create_fluid_sim, this is the rule to start with:
create_fluid_sim stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. 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 create_fluid_sim call is checked against it from then on.
Questions about create_fluid_sim
Build a real-time 2D fluid/ink/dye simulation (stable-fluids style: semi-Lagrangian advection + Jacobi pressure solve + gradient-subtract projection + dye advection) as a stack of GLSL TOPs in feedback loops inside a new baseCOMP under. It is categorised as a Write tool in the tdmcp — TouchDesigner MCP server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the tdmcp — TouchDesigner MCP server MCP server in PolicyLayer and add a rule for create_fluid_sim: 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.
create_fluid_sim 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 create_fluid_sim 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 create_fluid_sim. 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.
create_fluid_sim 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