@audiodn/mcp

Model Context Protocol server for AudioDN.

Exposes the AudioDN REST API as MCP tools so AI agents (Cursor, Claude Desktop, Claude Code, VS Code, Codex, etc.) can configure audio hosting on a user's behalf, plus offline, read-only knowledge tools grounded in the canonical AudioDN OpenAPI spec and documentation so agents look up the correct endpoints instead of guessing.

Install

npm install -g @audiodn/mcp
# or run on demand
npx @audiodn/mcp

Related MCP server: Audacity MCP Server

Configure

Set a server-side AudioDN API key (mint one in the dashboard at https://account.audiodeliverynetwork.com under Settings → API Keys).

export ADN_API_KEY="adn_..."
# Optional overrides:
# export ADN_API_BASE_URL="https://api.audiodelivery.net"  # default
# export ADN_MCP_ALLOW_DELETE=1     # enable destructive delete tools (off by default)
# export ADN_MCP_LIVE_DOCS=1        # refresh bundled docs from the public site at startup
# export ADN_MCP_TIMEOUT_MS=30000   # per-request timeout

Environment variables

Safety model

• Reads and knowledge tools are annotated read-only and always available.

• Create/update tools run with the API key but are annotated so MCP clients can prompt for approval; the client is the human-in-the-loop layer.

• The two delete tools (adn_delete_creator, adn_delete_collection) are hidden and refuse to run unless the server is started with ADN_MCP_ALLOW_DELETE=1. Set it once to opt in.

Use with Cursor

Settings → Tools & Integrations → MCP (or edit ~/.cursor/mcp.json):

{
  "mcpServers": {
    "audiodn": {
      "command": "npx",
      "args": ["-y", "@audiodn/mcp"],
      "env": { "ADN_API_KEY": "adn_..." }
    }
  }
}

Use with Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (or the equivalent on your OS), then restart the app:

{
  "mcpServers": {
    "audiodn": {
      "command": "npx",
      "args": ["-y", "@audiodn/mcp"],
      "env": { "ADN_API_KEY": "adn_..." }
    }
  }
}

Use with Claude Code

claude mcp add audiodn --env ADN_API_KEY=adn_... -- npx -y @audiodn/mcp

Use with VS Code (Copilot) / Codex / Windsurf

Any client that speaks MCP over stdio uses the same command. For VS Code, add to .vscode/mcp.json:

{
  "servers": {
    "audiodn": {
      "command": "npx",
      "args": ["-y", "@audiodn/mcp"],
      "env": { "ADN_API_KEY": "adn_..." }
    }
  }
}

For Codex CLI (~/.codex/config.toml):

[mcp_servers.audiodn]
command = "npx"
args = ["-y", "@audiodn/mcp"]
env = { ADN_API_KEY = "adn_..." }

Tools

Knowledge tools (read-only, offline, no API key needed)

Live API tools

Resources

The server also exposes canonical docs as MCP resources for clients that attach context directly: audiodn://openapi.json, audiodn://llms-full.txt, and audiodn://guide/{topic} for each guide.

Example flow

An agent helping a user host a podcast might call:

1. adn_get_guide({ topic: "upload" }) — learn the canonical multi-step flow.

2. adn_create_collection({ title: "My Podcast" })

3. adn_create_upload_session({ collection_id })

4. adn_create_track_in_upload_session({ upload_session_id, file_name: "ep1.mp3" })

5. Your code PUTs the audio bytes to track_upload.upload_url.

6. Poll adn_get_track({ track_id }) until track_status_id === "ready".

7. adn_create_play_session({ scope: "track", track_id }) — returns a signed playback URL that can be embedded directly.

Build from source

npm install
npm run build
npm test           # vitest
npm run smoke      # build + spawn the real binary over stdio
node dist/index.js

Keeping docs fresh

Bundled snapshots live in assets/snapshots/. Refresh them from the public site with npm run sync; prepublishOnly verifies they are consistent before a release.

Reference

• API docs: https://audiodeliverynetwork.com/docs/api

• OpenAPI spec: https://audiodeliverynetwork.com/openapi.json

• For-AI-agents guide: https://audiodeliverynetwork.com/for-ai-agents