@audiodn/mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@audiodn/mcpcreate a new collection for my podcast episodes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@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 in Cursor
One-click install (hosted endpoint, zero setup — knowledge/doc tools work immediately):
To enable the live API tools, set ADN_API_KEY (an adn_... key from the
dashboard) in your environment before launching Cursor; the hosted endpoint
picks it up from the Authorization header. Prefer a local stdio server? Use
this button instead:
Both correspond to the mcp.json shipped with this plugin. See
Cursor's MCP docs for manual setup.
Related MCP server: kokoro-tts
Install
npm install -g @audiodn/mcp
# or run on demand
npx @audiodn/mcpConfigure
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 timeoutEnvironment variables
Variable | Required | Default | Purpose |
| Yes | – | Server-side, full-access API key used for all live-API tools. |
| No |
| Override the API host. |
| No | off | Set to |
| No | off | Set to |
| No |
| Per-request timeout in milliseconds. |
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 withADN_MCP_ALLOW_DELETE=1. Set it once to opt in.
Hosted (remote) endpoint
Besides the local npx stdio server above, AudioDN runs the same tool set as a
hosted Streamable HTTP endpoint on Cloudflare Workers, so clients that
support remote MCP servers can connect without installing anything.
URL:
https://mcp.audiodelivery.net/mcp— the MCP endpoint. The root/serves a human landing page in a browser (and JSON for tooling), and/healthreturns machine-readable server info.Auth — bring your own key: the endpoint is public and stores no secrets. Knowledge/doc tools work with no key. To enable the live API tools, send your AudioDN API key on every request as either header:
Authorization: Bearer adn_...
# or
X-ADN-API-Key: adn_...Deletes are never exposed on the hosted endpoint, regardless of key.
Example client configuration (clients that support a remote/HTTP MCP URL):
{
"mcpServers": {
"audiodn": {
"url": "https://mcp.audiodelivery.net/mcp",
"headers": { "Authorization": "Bearer adn_..." }
}
}
}The hosted Worker lives in worker/ and is deployed with Wrangler
(npm run deploy); it is not part of the published npm package.
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/mcpUse 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)
Tool | Description |
| Server version, bundled OpenAPI version, docs source, API base. |
| Keyword search over bundled docs + OpenAPI summaries. |
| List all REST operations (operationId, method, path). |
| Full OpenAPI definition for one operationId. |
| Canonical guide (authentication, upload, processing, playback, webhooks, variant-types, security, compatibility). |
| The seven variant types and which are API-creatable. |
Live API tools
Tool | Description | Annotation |
| Read creators | read-only |
| Create/update creator | write |
| Delete creator | destructive (gated) |
| Read collections | read-only |
| Create/update collection | write |
| Delete collection + its tracks | destructive (gated) |
| Read tracks; | read-only |
| Manage upload sessions | write / read-only |
| Register a track, get | write |
| Mint/read play sessions (scope: collection, track) | write / read-only |
| List org delivery variants | read-only |
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:
adn_get_guide({ topic: "upload" })— learn the canonical multi-step flow.adn_create_collection({ title: "My Podcast" })adn_create_upload_session({ collection_id })adn_create_track_in_upload_session({ upload_session_id, file_name: "ep1.mp3" })Your code
PUTs the audio bytes totrack_upload.upload_url.Poll
adn_get_track({ track_id })untiltrack_status_id === "ready".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.jsDeploy the hosted endpoint
The Cloudflare Worker in worker/ serves the same tools over Streamable HTTP.
npx wrangler login
npm run dev:worker # local: http://localhost:8787/mcp and /health
npm run deploy # publish -> https://mcp.audiodelivery.net (custom domain)
curl https://mcp.audiodelivery.net/healthThe custom domain mcp.audiodelivery.net is provisioned by Cloudflare from the
routes entry in wrangler.toml (the audiodelivery.net zone must be on the
same Cloudflare account).
To list on the official MCP registry (registry name net.audiodelivery/mcp,
which must match mcpName in package.json): verify the domain once with
mcp-publisher login dns --domain audiodelivery.net (add the printed TXT
record), confirm remotes[0].url in server.json points at the deployed URL,
then mcp-publisher publish.
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
OpenAPI spec: https://audiodeliverynetwork.com/openapi.json
For-AI-agents guide: https://audiodeliverynetwork.com/for-ai-agents
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA comprehensive audio MCP server that enables AI agents to generate speech, transcribe audio, clone voices, analyze speech quality, design soundscapes, and manage audio assets through a standardized interface.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to generate high-quality speech with 54+ voices in multiple languages via MCP tools.17Apache 2.0
- AlicenseAqualityAmaintenanceRender, analyze, and verify audio (WAV or FLAC) through a fully offline, deterministic engine, exposed as MCP tools for AI agents.1213Apache 2.0
- FlicenseNot gradedqualityBmaintenanceExposes Stable Diffusion for text-to-image generation and GPT-SoVITS for text-to-speech synthesis as MCP tools, enabling image and audio generation via natural language.
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Hosted MCP with 91 agent tools: X, domains, SEO, Maps, Trends, Search, YouTube, TikTok, and more.
Connect any AI agent to 11+ social platforms: schedule, publish & track posts via hosted MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/audiodn/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server