Skip to main content
Glama

Import Shadertoy

import_shadertoy

Convert a Shadertoy shader (by URL, ID, or pasted source) into a GLSL TOP with automatic iChannel wiring, speed/mouse controls, and preview.

Instructions

Build a GLSL TOP from a Shadertoy URL, ID, or pasted source. Wires iChannels (defaulting to noise placeholders), exposes Speed (and optional Mouse) controls, and captures a preview. First fetch on macOS may trigger an outgoing-connection permission prompt. Set TDMCP_SHADERTOY_KEY for reliable fetches; paste into raw_source to stay offline.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
shader_idNoShadertoy 6-char ID, e.g. 'XsXXDn'.
urlNoFull Shadertoy URL: https://www.shadertoy.com/view/<id>.
raw_sourceNoPasted Shadertoy-style fragment (must contain mainImage). Offline-safe.
parent_pathNo/project1
nameNoshadertoy
resolutionNo
pixel_formatNorgba8
channelsNo
expose_mouse_controlNo
expose_speed_controlNo
capture_previewNo
provenance_overrideNo
Behavior4/5

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

Annotations indicate readOnlyHint=false (creates) and destructiveHint=false (non-destructive). Description adds a useful behavioral note: macOS may prompt for outgoing connection on first fetch. No contradictions.

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?

Two dense sentences with essential information front-loaded. No redundant text.

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

Completeness4/5

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

Given 12 parameters, no required params, no output schema, and sparse annotations, the description covers core behavior (import, wire channels, controls, preview, offline option) sufficiently for an agent to decide to use it. Minor omissions (resolution, pixel_format) are secondary.

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 low (25%), but the description adds meaning for key parameters: wires iChannels (maps to channels), exposes Speed and optional Mouse controls (maps to expose_speed_control, expose_mouse_control), and captures preview (capture_preview). However, many parameters like resolution, pixel_format, provenance_override are not explained. Partially compensates for low schema coverage.

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?

Clearly specifies the verb 'Build a GLSL TOP' from Shadertoy URL, ID, or pasted source. Distinguishes from siblings like import_isf_shader and create_glsl_shader by targeting Shadertoy specifically.

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?

Provides explicit when-to-use context: import via URL, ID, or pasted source. Mentions offline mode via raw_source and needing a key for reliable fetches. Though it doesn't directly compare with all siblings, the Shadertoy specificity implies differentiation.

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