watch_node
Read-only: sample one TouchDesigner operator over a short interval and return runtime state, readable parameter values, and CHOP channel values when available. Missing TD attributes/channels are reported as warnings instead of failing the watch. Returns {path, requested_samples, collected_samples...
This record as markdown: /tools/io-github-pantani-tdmcp/watch-node.md
What watch_node does on tdmcp — TouchDesigner MCP server
AI agents call watch_node 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 watch_node is rated Low
This tool performs pure data retrieval and monitoring of TouchDesigner operators. It samples state, reads parameters, and returns snapshots—all non-mutating operations. The 'Read-only' designation and the lack of any modification, creation, deletion, or execution capabilities clearly place this in the Read category with low severity, as misuse would only expose observable system state without causing side effects.
From the tool's definition Tool description explicitly states 'Read-only: sample one TouchDesigner operator over a short interval and return runtime state, readable parameter values, and CHOP channel values when available.' It collects and returns snapshots of state and parameters…
Attacks that exploit this kind of access
The rule that runs watch_node 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 watch_node, this is the rule to start with:
watch_node 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 watch_node call is checked against it from then on.
Questions about watch_node
Read-only: sample one TouchDesigner operator over a short interval and return runtime state, readable parameter values, and CHOP channel values when available. Missing TD attributes/channels are reported as warnings instead of failing the watch. Returns {path, requested_samples, collected_samples, interval_ms, window_ms, warnings[], snapshots[]} where each snapshot has {sample_index, elapsed_ms, path, type, family, state, parameters, channels, 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 watch_node: 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.
watch_node 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 watch_node 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 watch_node. 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.
watch_node 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