SunoMCP

suno_generate_with_custom_model

Generate music from a ready custom model with lyrics, style, or instrumental options; returns a task ID to poll for completion.

Instructions

Generate with a ready custom model, including instrumental or automatic lyrics.

Submission returns a task ID. Poll suno_get_task until finished_at is set and
inspect response.success. This operation never falls back to another model.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "suno_generate_with_custom_model"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Ready custom music model ID to generate with.
`lyric`	No	Lyrics; required unless instrumental or lyric_prompt is supplied.
`style`	No	Optional music style.
`title`	No	Optional song title.
`duration`	No	Requested duration in seconds; availability depends on the custom model.
`weirdness`	No
`callback_url`	No	HTTPS webhook for the completed task.
`instrumental`	No	Generate without vocals. Default false.
`lyric_prompt`	No	Generate lyrics from this description.
`vocal_gender`	No	Vocal preference: f or m.
`negative_tags`	No	Styles to exclude.
`style_influence`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedv0.1.25Nov 2, 2026

addedInput schema / properties / callback_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "HTTPS webhook for the completed task.",
+  "title": "Callback Url"
+}

addedInput schema / properties / duration

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Requested duration in seconds; availability depends on the custom model.",
+  "title": "Duration"
+}

addedInput schema / properties / instrumental

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Generate without vocals. Default false.",
+  "title": "Instrumental"
+}

addedInput schema / properties / lyric / default
```
Added value: +""
```

changedInput schema / properties / lyric / description

Previous value: -"Lyrics for the generated song."New value: +"Lyrics; required unless instrumental or lyric_prompt is supplied."

addedInput schema / properties / lyric_prompt

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Generate lyrics from this description.",
+  "title": "Lyric Prompt"
+}

addedInput schema / properties / negative_tags

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Styles to exclude.",
+  "title": "Negative Tags"
+}

addedInput schema / properties / style / default
```
Added value: +""
```

changedInput schema / properties / style / description

Previous value: -"Music style for the generated song."New value: +"Optional music style."

addedInput schema / properties / style_influence

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 1,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Style Influence"
+}

addedInput schema / properties / title / default
```
Added value: +""
```

changedInput schema / properties / title / description

Previous value: -"Title for the generated song."New value: +"Optional song title."

addedInput schema / properties / vocal_gender

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "",
+        "f",
+        "m"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Vocal preference: f or m.",
+  "title": "Vocal Gender"
+}

addedInput schema / properties / weirdness

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 1,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Weirdness"
+}

changedInput schema / required

Previous value: -[
-  "id",
-  "title",
-  "lyric",
-  "style"
-]New value: +[
+  "id"
+]

Addedv0.1.15Sep 5, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description genuinely carries the load: it discloses that the call is asynchronous and returns a task ID, that completion must be polled via suno_get_task, that success must be checked via response.success, and that there is no fallback to another model. It omits cost/credit or permission implications of a generation call, which keeps it short of a 5.

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?

Three compact sentences, each front-loaded with an actionable fact: what it does, how to confirm the async result, and the no-fallback constraint. No filler and nothing buried.

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?

For a 12-parameter generation tool with an output schema and high schema coverage, the description supplies what structured fields cannot: the async task lifecycle and the no-fallback trait. It stops short only on prerequisites for obtaining a 'ready' model ID and any cost implication.

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 coverage is high (83%), so the schema already documents id, lyric, instrumental, callback_url, lyric_prompt and others, making a baseline of 3 appropriate. The description's only added meaning is the instrumental/automatic-lyrics dichotomy; the undocumented params (weirdness, style_influence) are left unexplained in both places.

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 and resource: generate audio using a ready custom model, with instrumental or automatic lyrics. This is clear but does not explicitly distinguish itself from the similarly named siblings suno_generate_custom_music and suno_generate_music, so the reader must infer that 'custom model' means a model object rather than custom music.

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 gives a concrete post-call workflow (poll suno_get_task until finished_at is set, inspect response.success) and a useful non-behavior ('never falls back to another model'). However, it never states when to prefer this over suno_generate_music or suno_generate_custom_music, or what prerequisite produces a 'ready' model ID.

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

Deploy Server