RMCP.DEV
← Registry

Content Tools

soundside.ai

Manages library entities and creates videos and images from text prompts.

x402 supported1 endpoint19 known toolsFirst detected July 17, 2026Last detected August 25, 2026

ENDPOINT 1

https://mcp.soundside.ai/mcp

No auth detected

MCP server metadata

Name
soundside-mcp
Version
1.27.1
Capabilities
experimentalpromptsresourcestoolstasks.listtasks.canceltasks.requests.tools.call
Server instructions

Soundside MCP server — AI-powered media generation, editing, and library management.

Known tools 19

lib_list

List library entities: projects, collections, resources, lineage, brand_kits, credits, or dashboard (composite load).

Inferred read-only
lib_manage

CRUD for library entities (projects, collections, resources, brand_kits).

Inferred read-only
lib_share

Manage project sharing: share by email, list shares, or revoke access.

Potential side effects
create_video

Create video from text/image.

Potential side effects
create_image

Create image from text prompt or reference.

Potential side effects
create_audio

Create audio: TTS, sound effects, voice cloning/design, or list_voices.

Potential side effects
create_music

Create music from lyrics/prompt.

Potential side effects
create_text

Generate text via LLM chat completions.

Inferred read-only
create_artifact

Create a business artifact: presentation (slides), chart (data viz), document (sections), or diagram (mermaid).

Potential side effects
train_adapter

Train a LoRA adapter from library media.

Inferred read-only
list_adapters

List LoRA adapters mirrored into the Soundside library.

Inferred read-only
manage_adapter

Manage a LoRA adapter: inspect, deploy, undeploy, delete, or select_checkpoint.

Potential side effects
edit_video

Edit video: trim, concat, crossfade, adjust_speed, loop, color_grade, custom, burn_subtitles.

Potential side effects
compose_media

Layer text, images, or video onto a base video: add_text, overlay, split_screen.

Inferred read-only
edit_audio

Edit audio on video: mix_audio, replace_audio, pad_audio.

Potential side effects
apply_effect

Cinematic effects: ken_burns (image→video motion), speed_ramp, film_grain, vignette.

Inferred read-only
extract_media

Extract from media: extract_frame, extract_frames, extract_audio.

Inferred read-only
analyze_media

Analyze media: technical metadata, vision_qa, transcribe, detect_segments, export_edl.

Inferred read-only
compose_video

Compose a complete video from a timeline plan.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.soundside-mcp]
url = "https://mcp.soundside.ai/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "soundside-mcp": {
      "type": "http",
      "url": "https://mcp.soundside.ai/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: soundside-mcp
Remote MCP URL: https://mcp.soundside.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "soundside-mcp": {
      "url": "https://mcp.soundside.ai/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code 
{
  "servers": {
    "soundside-mcp": {
      "type": "http",
      "url": "https://mcp.soundside.ai/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "soundside-mcp",
  "transport": "streamable-http",
  "url": "https://mcp.soundside.ai/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for soundside.ai was fetched 2026-08-03T21:20:31.602Z and is being refreshed.

Trust status Neutral

soundside.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.