ideogram-mcp

ideogram_generate

Generate images from text prompts using Ideogram 3.0 or 4.0, with control over resolution, style, references, and color palettes.

Instructions

Generate images from text prompts with Ideogram 3.0 (default) or 4.0 (model: '4.0'). 3.0 takes aspect ratios or an exact resolution, style types, style and character reference images, style codes, presets, colour palettes and custom models.

Input Schema

TableJSON Schema

Name	Required	Description
`seed`	No	Reproducibility seed (0-2,147,483,647)
`model`	No	Ideogram model: 3.0 (default; every parameter below) or 4.0 (text prompt, resolution, rendering_speed except FLASH, enable_copyright_detection — the other parameters are refused)
`prompt`	Yes	Image description (1-10,000 characters)
`num_images`	No	Number of images to generate (1-8, default: 1)
`resolution`	No	Exact output resolution: one of Ideogram 3.0's 69 sizes, or any WIDTHxHEIGHT for model 4.0; not with aspect_ratio
`style_type`	No	Visual style (the API default is GENERAL when omitted)
`style_codes`	No	8-character hexadecimal style codes from Ideogram
`aspect_ratio`	No	Output aspect ratio (default: 1x1)
`magic_prompt`	No	Auto-enhance prompts (default: AUTO)
`style_preset`	No	A named style preset as Ideogram lists them
`color_palette`	No	A preset palette by name, or explicit colours with weights (not both)
`negative_prompt`	No	What to exclude from the generated image
`rendering_speed`	No	Speed/quality tradeoff. FLASH=fastest, QUALITY=best (default: DEFAULT)
`custom_model_uri`	No	A custom (trained) model: model/<name>/version/<version>
`style_reference_images`	No	Local image files whose style the result follows (up to 3, 25 MB each)
`character_reference_mask`	No	Grayscale mask of the character reference (same dimensions); needs character_reference_image
`character_reference_image`	No	Local image file of a character to keep consistent (one image; Ideogram bills character references at its own rate)
`enable_copyright_detection`	No	true runs Ideogram's copyright detection on this request; false leaves the organisation setting in force (it cannot switch an organisation-wide detection off)

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv1.2.0Oct 2, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / character_reference_image

Added value: +{
+  "description": "Local image file of a character to keep consistent (one image; Ideogram bills character references at its own rate)",
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / character_reference_mask

Added value: +{
+  "description": "Grayscale mask of the character reference (same dimensions); needs character_reference_image",
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / color_palette

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "name": {
+          "description": "A preset palette",
+          "enum": [
+            "EMBER",
+            "FRESH",
+            "JUNGLE",
+            "MAGIC",
+            "MELON",
+            "MOSAIC",
+            "PASTEL",
+            "ULTRAMARINE"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "name"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "members": {
+          "description": "Explicit colours, most dominant first",
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "color_hex": {
+                "description": "The colour, #RRGGBB",
+                "pattern": "^#[0-9A-Fa-f]{6}$",
+                "type": "string"
+              },
+              "color_weight": {
+                "description": "Its share of the palette (0.05-1)",
+                "maximum": 1,
+                "minimum": 0.05,
+                "type": "number"
+              }
+            },
+            "required": [
+              "color_hex"
+            ],
+            "type": "object"
+          },
+          "maxItems": 10,
+          "minItems": 1,
+          "type": "array"
+        }
+      },
+      "required": [
+        "members"
+      ],
+      "type": "object"
+    }
+  ],
+  "description": "A preset palette by name, or explicit colours with weights (not both)"
+}

addedInput schema / properties / custom_model_uri

Added value: +{
+  "description": "A custom (trained) model: model/<name>/version/<version>",
+  "pattern": "^model\\/[^/\\s]+\\/version\\/[^/\\s]+$",
+  "type": "string"
+}

addedInput schema / properties / enable_copyright_detection

Added value: +{
+  "description": "true runs Ideogram's copyright detection on this request; false leaves the organisation setting in force (it cannot switch an organisation-wide detection off)",
+  "type": "boolean"
+}

addedInput schema / properties / model

Added value: +{
+  "description": "Ideogram model: 3.0 (default; every parameter below) or 4.0 (text prompt, resolution, rendering_speed except FLASH, enable_copyright_detection — the other parameters are refused)",
+  "enum": [
+    "3.0",
+    "4.0"
+  ],
+  "type": "string"
+}

addedInput schema / properties / resolution

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "512x1536",
+        "576x1408",
+        "576x1472",
+        "576x1536",
+        "640x1344",
+        "640x1408",
+        "640x1472",
+        "640x1536",
+        "704x1152",
+        "704x1216",
+        "704x1280",
+        "704x1344",
+        "704x1408",
+        "704x1472",
+        "736x1312",
+        "768x1088",
+        "768x1216",
+        "768x1280",
+        "768x1344",
+        "800x1280",
+        "832x960",
+        "832x1024",
+        "832x1088",
+        "832x1152",
+        "832x1216",
+        "832x1248",
+        "864x1152",
+        "896x960",
+        "896x1024",
+        "896x1088",
+        "896x1120",
+        "896x1152",
+        "960x832",
+        "960x896",
+        "960x1024",
+        "960x1088",
+        "1024x832",
+        "1024x896",
+        "1024x960",
+        "1024x1024",
+        "1088x768",
+        "1088x832",
+        "1088x896",
+        "1088x960",
+        "1120x896",
+        "1152x704",
+        "1152x832",
+        "1152x864",
+        "1152x896",
+        "1216x704",
+        "1216x768",
+        "1216x832",
+        "1248x832",
+        "1280x704",
+        "1280x768",
+        "1280x800",
+        "1312x736",
+        "1344x640",
+        "1344x704",
+        "1344x768",
+        "1408x576",
+        "1408x640",
+        "1408x704",
+        "1472x576",
+        "1472x640",
+        "1472x704",
+        "1536x512",
+        "1536x576",
+        "1536x640"
+      ],
+      "type": "string"
+    },
+    {
+      "pattern": "^\\d{3,4}x\\d{3,4}$",
+      "type": "string"
+    }
+  ],
+  "description": "Exact output resolution: one of Ideogram 3.0's 69 sizes, or any WIDTHxHEIGHT for model 4.0; not with aspect_ratio"
+}

addedInput schema / properties / style_codes

Added value: +{
+  "description": "8-character hexadecimal style codes from Ideogram",
+  "items": {
+    "pattern": "^[0-9A-Fa-f]{8}$",
+    "type": "string"
+  },
+  "maxItems": 8,
+  "minItems": 1,
+  "type": "array"
+}

addedInput schema / properties / style_preset

Added value: +{
+  "description": "A named style preset as Ideogram lists them",
+  "maxLength": 100,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / style_reference_images

Added value: +{
+  "description": "Local image files whose style the result follows (up to 3, 25 MB each)",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 3,
+  "minItems": 1,
+  "type": "array"
+}

changedInput schema / properties / style_type / description

Previous value: -"Visual style (default: AUTO)"New value: +"Visual style (the API default is GENERAL when omitted)"

First observedv1.0.3Sep 25, 2026

TDQS

B3.1/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, yet it offers no cost, rate-limit, latency, or output-handling information. The feature list for 3.0 largely duplicates what the schema already documents, adding minimal behavioral insight beyond the default-model note.

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?

Two sentences with the model/version distinction front-loaded. The second sentence is a somewhat loose enumeration, but it stays short and every clause maps to real capability.

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

Completeness2/5

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

For an 18-parameter generative tool with no annotations and no output schema, the description is thin: it says nothing about return values, asynchronous generation, or billing implications of reference images. It does not compensate for the absent structured context.

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 each of the 18 parameters is already documented in detail. The description's parameter mentions (aspect ratios, resolution, style codes, presets, palettes) restate schema content without adding format or interaction detail, so the baseline 3 applies.

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

Purpose4/5

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

The description states a specific verb+resource ('Generate images from text prompts') and identifies the two model versions with the default flagged. It doesn't differentiate itself from siblings like ideogram_edit or ideogram_remix, but the core purpose is unambiguous.

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

Usage Guidelines3/5

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

It notes that 3.0 is the default and that 4.0 is opt-in via model: '4.0', and lists what 3.0 supports, which implicitly guides model choice. However it never states when to prefer 4.0 over 3.0, nor when to use this tool versus edit/remix/upscale siblings.

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

Deploy Server

ideogram_generate

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools