Koskamo

Suede AI MCP

Provides a Model Context Protocol endpoint for accessing Suede AI's agentic commerce catalog, enabling agents to discover and utilize paid creative products including music, video, and image generation services.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Suede AI MCP logo, by Suede AICommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Suede AI
MCP endpoint (Streamable HTTP)
https://app.suedeai.ai/api/mcp
Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

5 of 5 have a description · 0 of 5 declare behavior hints · 5 of 5 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Discover paid creative products via the agentic commerce catalog
  • Access music, video, and image generation tools
  • Integrate USDC payments on Base via x402
  • Utilize Stripe Checkout via Agentic Commerce Protocol

Source and maintenance

Community listingRegistry 0.1.0
Maintenance checked

Protocol and capabilities

Server
suede-agentic-commerce 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
5 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Suede AI agentic-commerce skills (music, video, and image generation). Every tool is x402-payable in USDC on Base. tools/list returns the full catalog with inputSchemas; tools/call returns a payment-required pointer. For a Skyfire buyer, use skyfire_create_music with a PAY token scoped to the Create Music seller service, then skyfire_get_music to poll the song without another charge.

Tools

5 advertised

create_music
Advertised by the server during the last successful anonymous check.

AI music generation from a text prompt. Creates a complete original song with vocals, melody, and full arrangement as a finished MP3, not a loop or preview. Describe genre, mood, instrumentation, and tempo, supply your own lyrics, request an instrumental, or pin a style tag. Use for soundtracks under video, release-ready artist tracks, podcast and game themes, and demo sketches. Async: poll songId until model_version leaves 'pending'. — $0.50 USDC via x402 on Base (chain 8453).

create_music input schema
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "tags": {
      "type": "string",
      "description": "Comma-separated keywords to tag the generated file."
    },
    "style": {
      "type": "string",
      "description": "Specific musical style or genre tag (e.g., 'Hip Hop', 'Ambient', 'Rock'). Helping the AI focus on a specific sound."
    },
    "lyrics": {
      "type": "string",
      "description": "Your custom lyrics. Required if custom_mode is true."
    },
    "prompt": {
      "type": "string",
      "description": "Describe the song you want to create. Include genre, mood, instruments, and any specific vibe. Example: 'Upbeat 80s synthwave with driving bass and neon atmosphere' or 'A melancholic acoustic guitar ballad about rain'."
    },
    "custom_mode": {
      "type": "boolean",
      "description": "Set to true to use your own lyrics provided in the 'lyrics' field."
    },
    "vocal_gender": {
      "enum": [
        "m",
        "f"
      ],
      "type": "string",
      "description": "Preferred gender for the vocalist ('m' for male, 'f' for female)."
    },
    "durationSeconds": {
      "type": "integer",
      "default": 120,
      "maximum": 120,
      "minimum": 5,
      "description": "Duration of the track in seconds. Defaults to a full-length song."
    },
    "make_instrumental": {
      "type": "boolean",
      "description": "If true, generates a track without vocals."
    }
  }
}
agent_video
Advertised by the server during the last successful anonymous check.

AI video generation from a text prompt. Returns an 8-second 720p clip with native audio. Use for short-form video, b-roll, product shots, music-video visuals, social clips, and ads. Include sound cues (instruments, voices, weather, movement) since audio is generated from the scene; a silent scene renders near-silent by design. Async by default: poll the returned pollUrl for videoUrl, or pass ?async=false to block. — $4.99 USDC via x402 on Base (chain 8453).

agent_video input schema
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "description": "Optional random seed for reproducible renders."
    },
    "model": {
      "type": "string",
      "description": "Optional model preset variant. Leave unset for the default."
    },
    "prompt": {
      "type": "string",
      "description": "Narrative or visual prompt to drive the music video concept."
    },
    "asyncMode": {
      "type": "boolean",
      "description": "Return immediately with a jobId while the render runs. Can only switch async on: false is the same as omitting it, so a paid call stays asynchronous; ?async=false is the only way to force a blocking call."
    },
    "resolution": {
      "enum": [
        "720p",
        "1024p"
      ],
      "type": "string",
      "description": "Target rendering resolution."
    },
    "aspectRatio": {
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "type": "string",
      "description": "Desired frame aspect ratio."
    },
    "durationSeconds": {
      "type": "integer",
      "description": "Clip length in seconds (default 8)."
    }
  }
}
agent_image
Advertised by the server during the last successful anonymous check.

AI image generation from a text prompt. Generate album and single cover art, podcast and video thumbnails, social and campaign graphics, concept art, storyboard frames, product shots, and article illustrations. Returns one hosted still image as PNG or JPEG in square, portrait, or widescreen framing (1:1, 4:5, 9:16, 16:9, 21:9). Async by default: poll the returned pollUrl for imageUrl, or pass ?async=false to block. — $0.15 USDC via x402 on Base (chain 8453).

agent_image input schema
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Image description — subject, style, composition."
    },
    "asyncMode": {
      "type": "boolean",
      "description": "Return immediately with a jobId while the render runs. Can only switch async on: false is the same as omitting it, so a paid call stays asynchronous; ?async=false is the only way to force a blocking call."
    },
    "aspectRatio": {
      "type": "string",
      "description": "Aspect ratio, e.g. '1:1', '16:9', '9:16'."
    }
  }
}
skyfire_create_music
Advertised by the server during the last successful anonymous check.

Generate one original song using a Skyfire PAY token scoped to seller service ea133c15-9ed4-4346-ad48-990b10aa1c87. The backend charges $0.50 USDC; it also accepts x402 payments. Supply the Skyfire token privately, never quote it in the answer. Paid calls queue a job; use skyfire_get_music to poll it. Do not retry a paid call without checking its outcome.

skyfire_create_music input schema
{
  "type": "object",
  "required": [
    "prompt",
    "skyfireToken"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Original song description."
    },
    "skyfireToken": {
      "type": "string",
      "description": "Skyfire PAY or KYA-PAY token scoped to the Suede Create Music seller service. Treat as a bearer secret."
    },
    "make_instrumental": {
      "type": "boolean",
      "description": "Generate without vocals."
    }
  },
  "additionalProperties": false
}
skyfire_get_music
Advertised by the server during the last successful anonymous check.

Poll a Create Music songId for the finished track. This GET is free and does not require a Skyfire token or another x402 USDC payment.

skyfire_get_music input schema
{
  "type": "object",
  "required": [
    "songId"
  ],
  "properties": {
    "songId": {
      "type": "string",
      "description": "songId returned by skyfire_create_music."
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1186 ms
95th percentile latency
1186 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1186 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http suede-ai-mcp https://app.suedeai.ai/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add suede-ai-mcp --url https://app.suedeai.ai/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable suede-ai-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "suede-ai-mcp": {
      "url": "https://app.suedeai.ai/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "suede-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://app.suedeai.ai/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start suede-ai-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "suede-ai-mcp": {
      "type": "http",
      "url": "https://app.suedeai.ai/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http suede-ai-mcp https://app.suedeai.ai/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://app.suedeai.ai/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "suede-ai-mcp": {
      "serverUrl": "https://app.suedeai.ai/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Suede AI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.