SunoMCP

suno_generate_inspo

Generate a brand-new song inspired by 1–4 reference audio tracks. Use prompt and style tags to draw stylistic inspiration without copying the sources.

Instructions

Generate brand-new music inspired by 1 to 4 reference audios (Suno Inspo / 灵感创作).

Unlike a cover, inspo does not reproduce the source tracks - it draws stylistic
inspiration from them and composes a fresh song guided by your prompt and style tags.

Use this when:
- You have reference tracks whose vibe you want to riff on
- You want a new song "in the style of" some audio you provide

Returns:
    Task ID and generated audio information including URLs, title, lyrics, and duration.

Input Schema

Name	Required	Description	Default
`lyric`	No	Lyrics in custom mode; ignored for instrumental generation.
`model`	No	Suno model version to use for the inspired generation.	chirp-v5-5
`style`	No	Optional music style tags. Examples: 'acoustic, folk, warm', 'lo-fi, chill, instrumental'
`title`	No	Optional title of the song.
`custom`	No	Enable custom mode; use lyric or lyric_prompt for lyrics.
`prompt`	No	Optional lyrics or creative brief for the new song. Leave empty to let Suno write its own lyrics.
`audio_urls`	Yes	1 to 4 publicly accessible reference audio URLs used as inspiration. Suno extracts stylistic ideas from these tracks (rather than copying them) to create a brand-new song. Tip: avoid well-known catalog recordings, which may be rejected by Suno's copyright check.
`persona_id`	No	Voice ID, not an audio ID. Availability with Inspo depends on the service channel.
`audio_weight`	No	How strongly the reference audios influence the result, 0 to 1. Higher means closer to the references' vibe.
`callback_url`	No	Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when generation completes.
`instrumental`	No	Generate instrumental music without lyrics.
`lyric_prompt`	No	Auto-lyric prompt, only when custom=true and lyric is empty.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.1.25Nov 2, 2026

addedInput schema / properties / audio_urls / maxItems
```
Added value: +4
```
addedInput schema / properties / audio_urls / minItems
```
Added value: +1
```

addedInput schema / properties / custom

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Enable custom mode; use lyric or lyric_prompt for lyrics.",
+  "title": "Custom"
+}

addedInput schema / properties / instrumental

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Generate instrumental music without lyrics.",
+  "title": "Instrumental"
+}

addedInput schema / properties / lyric

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Lyrics in custom mode; ignored for instrumental generation.",
+  "title": "Lyric"
+}

addedInput schema / properties / lyric_prompt

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Auto-lyric prompt, only when custom=true and lyric is empty.",
+  "title": "Lyric Prompt"
+}

addedInput schema / properties / persona_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Voice ID, not an audio ID. Availability with Inspo depends on the service channel.",
+  "title": "Persona Id"
+}

Changed1 schema field changedv0.1.18Sep 10, 2026

changedInput schema / properties / model / enum

Previous value: -[
-  "chirp-v3-0",
-  "chirp-v3-5",
-  "chirp-v4",
-  "chirp-v4-5",
-  "chirp-v4-5-plus",
-  "chirp-v5",
-  "chirp-v5-5"
-]New value: +[
+  "chirp-v6",
+  "chirp-v6-wild",
+  "chirp-v6-mini",
+  "chirp-v3-0",
+  "chirp-v3-5",
+  "chirp-v4",
+  "chirp-v4-5",
+  "chirp-v4-5-plus",
+  "chirp-v5",
+  "chirp-v5-5"
+]

Addedv0.1.7Jun 21, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does add real behavioral context: it discloses that generation is asynchronous (returns a Task ID), and warns that well-known catalog recordings may be rejected by Suno's copyright check — a failure mode an agent could not infer from the schema. It omits cost/credit implications and processing-time expectations, keeping 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.

Conciseness4/5

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

Front-loaded with the core action, then the cover contrast, then a scannable 'Use this when' list, then returns. Slightly padded — the parenthetical dual-language name and a returns block that duplicates output-schema content are low-value — but no sentence is confusing or out of order.

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?

For a 12-param generation tool whose parameters are fully documented in schema and which has an output schema, the description supplies what structured fields cannot: the inspo-vs-cover distinction, async task semantics, and the copyright rejection caveat. Nothing an agent needs to invoke it correctly is missing.

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 every parameter is already documented, including the audio_urls copyright tip and audio_weight semantics. The description only echoes the 1-4 reference-audio limit and mentions prompt/style tags generically, adding no syntax or format detail beyond the schema. Baseline 3 applies.

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?

States a specific verb and resource ('Generate brand-new music inspired by 1 to 4 reference audios') and immediately delimits it against the nearest sibling concept: 'Unlike a cover, inspo does not reproduce the source tracks.' An agent can distinguish this from suno_cover_music and suno_generate_music without opening either schema.

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?

An explicit 'Use this when' block names two concrete selection conditions (reference tracks to riff on; 'in the style of' requests) and the cover contrast functions as an exclusion. It does not name sibling tools directly or say when to prefer suno_generate_music / suno_upload_extend instead, so routing is clear but not exhaustive.

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

Deploy Server