Skip to main content
Glama

Create capture loop

create_capture_loop

Build a bidirectional video bridge between TouchDesigner and another app (e.g., Resolume or OBS) using NDI, Syphon, or Spout. Supports receive, send, or full round-trip loop with anti-feedback isolation.

Instructions

Build a bidirectional inter-app video bridge to another program (Resolume, OBS, MadMapper, a game engine…) in one container: receive an external feed IN and publish a TOP OUT at the same time. Picks the right operators per protocol — NDI (network, macOS & Windows), or Syphon (macOS) / Spout (Windows). direction 'in' only subscribes, 'out' only publishes, 'both' runs a full round-trip loop. The receive half is a receiver TOP → Null 'in_out'; the send half pulls source_top through a Select TOP into a publisher TOP. ANTI-FEEDBACK: the two halves are never wired together, so 'both' won't loop this app's own output back in. PLATFORM-GATED & largely UNVERIFIED-live: Spout needs Windows, Syphon needs macOS, and sender/receiver-name parameter names vary by TD build (probed at runtime) — the wrong platform or a real signal needs the actual sender present. This is the combined in+out version of create_live_source (in) and setup_output (out).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
parent_pathNoCOMP to build the capture-loop container in (e.g. '/project1')./project1
nameNoBase name for the container COMP that holds the in/out bridge.capture_loop
protocolNoInter-app video transport. ndi works on macOS & Windows (network). spout is Windows-only; syphon is macOS-only — both use the same Syphon/Spout TOPs in TouchDesigner (PLATFORM-GATED: the wrong platform fails to create the op, reported as a warning).ndi
directionNoin: only receive an external feed. out: only publish a TOP. both: do both at once (a full round-trip loop to another app, e.g. send to Resolume and receive its output back).both
sender_nameNo(out) The public name THIS app publishes its feed under, so the other app can find it. Used for direction 'out'/'both'.tdmcp_out
receiver_nameNo(in) The name of the EXTERNAL sender to subscribe to. Empty = pick the first available sender on the network/machine. Used for direction 'in'/'both'.
source_topNo(out) Path of the TOP to publish when direction includes 'out' (e.g. '/project1/final'). Empty together with an 'out' direction publishes nothing and is flagged as a warning.
resolutionNoWorking resolution [w, h] applied to the receiver TOP (Output Resolution = Custom). The publisher inherits its input TOP's resolution.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide minimal info (no readOnly/destructive hints). The description adds significant behavioral context: protocol selection logic, anti-feedback wiring, platform-gated behavior, and the unverified-live nature. This goes well beyond the structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections and front-loaded purpose. It could be slightly more concise, but every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description comprehensively explains the tool's behavior, including anti-feedback, platform requirements, and relationship to sibling tools. It provides sufficient context for proper usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description does not add substantial meaning beyond the schema's parameter descriptions, though it provides helpful context about protocol and direction semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verbs ('Build', 'receive', 'publish') and resources ('bidirectional inter-app video bridge', 'receiver TOP', 'publisher TOP'). It clearly distinguishes from siblings by naming create_live_source (in) and setup_output (out) as alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states when to use this tool (combined in+out version of create_live_source and setup_output) and provides context on platform-gating and anti-feedback. However, it does not explicitly state when not to use it or provide exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Pantani/tdmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server