Skip to main content
Glama

Create AI Mirror

create_ai_mirror

Sets up an AI mirror with camera or synthetic input, live StreamDiffusion processing, and configurable output (Syphon/Spout/NDI/internal). Includes a control panel for prompt, strength, and CFG.

Instructions

Layer 1 COMBO: wires the canonical 2026 AI-mirror installation in one MCP call — camera (or synthetic / existing TOP) → StreamDiffusion (img2img live, delegated to drive_streamdiffusion) → Syphon/Spout/NDI/internal output → a prompt+strength+cfg control panel whose sliders and textDATs drive SD pars via .expr expressions. Panel only binds pars present in drive_streamdiffusion's validated_pars; missing pars are warned, not errored. Camera source on macOS triggers the OS permission dialog on first cook; fallback_to_synthetic keeps the rig alive when the camera is unavailable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
parent_pathNoParent COMP./project1
nameNoContainer name.ai_mirror
sourceNoInput source: USB camera (hype default), self-animated synthetic TOP, or an existing TOP routed through a Select.camera
existing_top_pathNoRequired when source='existing_top'.
camera_device_idxNoUSB camera device index when source='camera'.
fallback_to_syntheticNoIf camera creation fails, build a synthetic noise source instead of aborting.
promptNoInitial StreamDiffusion prompt.ethereal water
negative_promptNoInitial StreamDiffusion negative prompt.blurry, low quality, deformed
strengthNoimg2img mix; surfaced in the panel.
cfgNoClassifier-free guidance scale; SD sweet spot 1–2.
stepsNoStreamDiffusion 1–4 step LCM.
seedNo-1 = random per frame.
output_modeNoOutput: syphon_spout (macOS/Windows showcase form), ndi (cross-host), or internal (no sender).syphon_spout
output_sender_nameNoSender / NDI name.ai_mirror
expose_control_panelNoBuild the prompt+sliders panel and wire .expr expressions to SD pars.
show_camera_previewNoAdd a small selectTOP preview of the camera inside the panel.
Behavior5/5

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

The description discloses critical behavioral details beyond the annotations: macOS permission dialog on first cook, fallback_to_synthetic to keep the rig alive, panel behavior (binding only validated pars, warnings instead of errors). Given openWorldHint=true and no other annotations, the description fully shoulders the transparency burden.

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

Conciseness5/5

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

The description is a single paragraph of five sentences, each packing essential information. It front-loads the main purpose ('wires the canonical 2026 AI-mirror installation') and efficiently covers platform details, edge cases, and parameter interactions without waste or redundancy.

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 16 parameters, no output schema, and the complexity of the tool (camera, StreamDiffusion, output modes, control panel), the description covers the main pipeline, fallback behavior, parameter binding, and platform-specific notes. It provides enough context for an agent to understand the tool's operation and constraints completely.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining how parameters interact (e.g., sliders and textDATs drive SD pars via .expr expressions, panel only binds pars from drive_streamdiffusion's validated_pars). This integration context exceeds mere schema repetition.

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 explicitly states the tool wires the 'canonical 2026 AI-mirror installation in one MCP call' and lists the pipeline components (camera → StreamDiffusion → output → control panel). It clearly distinguishes itself by specifying 'Layer 1 COMBO' and detailing specific behaviors, making it unambiguous among sibling tools.

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 provides context for when to use the tool (e.g., for a Layer 1 COMBO installation, with fallback options) and explains edge cases such as missing parameter warnings and macOS permission dialogs. However, it does not explicitly state when not to use this tool or compare it to alternatives like drive_streamdiffusion alone.

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