hydra-mcp

hydra_video_out

Start or stop broadcasting the browser canvas as a live Syphon/NDI video source, then verify sent and published frame rates and dropped frames to confirm output quality.

Instructions

Send the primary tab's canvas out of the browser as a native video source: a Syphon server named "Hydra" (macOS). TouchDesigner receives it with a Syphon Spout In TOP. TouchDesigner names Syphon senders App:Server, and the publisher runs as Python, so the sender to pick is "Python:Hydra" — plain "Hydra" matches nothing and leaves the TOP on its checkerboard.

With hydra_out.py started with --ndi, the same frames also go out as an NDI source, which receivers list as " (Hydra)". NDI reaches other machines on the network; ndi_connections in the status says whether anything is receiving it.

action: "start", "stop" or "status". fps: 1–60, the capture rate to request.

Needs out/hydra_out.py running — a separate process with its own Python 3.12, because the Syphon library only supports up to 3.12 (see the README). Start waits two seconds, then returns both ends: page_after_2s sent_fps, dropped — what the tab actually sent out_after_2s fps, syphon_clients — what was published, and whether anything is receiving Report those numbers, not the fps you asked for. Frames are dropped rather than queued when the receiver lags, so a high dropped means lower the resolution (hydra_transport) or the fps.

Chromium tabs only (MediaStreamTrackProcessor). The primary must stay visible: a hidden tab stops producing frames.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`fps`	No
`action`	No		status

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 14, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond annotation's readOnlyHint=false, the description details the start/stop/status behavior, the two-second wait, the returned end-point objects, the fact that frames are dropped rather than queued when the receiver lags, and the consequence for a hidden tab. It also warns that plain 'Hydra' matches nothing in TouchDesigner, which is highly valuable behavioral insight not discoverable from annotations.

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 text is organized into a flow from purpose to receiver integration to parameter semantics, prereqs, and returned values. It is somewhat dense but every sentence conveys operational knowledge. It is not as tight as a two-sentence definition but it earns its length with whole paragraphs containing non-redundant detail.

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?

Given the simplicity of the schema and the lack of a clear output schema in the provided, the description is complete: it covers prerequisites, action semantics, fps meaning, output values, receiver behavior, failure modes, and a workaround (lower hydra_transport resolution/fps). The agent can call and interpret the result correctly without additional information.

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

Parameters5/5

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

Schema coverage is 0%, so the description carries the full burden of parameter explanation. It defines 'action' with allowed values start/stop/status and 'fps' with a 1–60 range and the meaning of the capture rate. It also tells the agent to report the returned fps rather than the requested fps, adding behavioral semantics to a parameter that otherwise has none in the schema.

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 opens with a specific verb and resource: 'Send the primary tab's canvas out of the browser as a native video source...' It clearly distinguishes itself by describing Syphon and NDI output, which none of the sibling tools (hydra_source, hydra_render, etc.) imply. The exact in-tool destination and the reason to pick 'Python:Hydra' over 'Hydra' makes the purpose unambiguous.

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 gives strong usage context: the external out/hydra_out.py must be running, Chromium is the only supported tab type, and the primary tab must remain visible (a hidden tab stops producing frames). It does not explicitly name alternatives or say when not to use it in favor of a sibling, but the prerequisites and operational constraints are clear enough to guide an agent correctly.

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