Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
CC0 sound effects API for AI agents — search, preview, and download via MCP.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://api.lotsofsounds.com/mcpRun this in your terminal
claude mcp add --transport http lotsofsounds https://api.lotsofsounds.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"lotsofsounds": {
"url": "https://api.lotsofsounds.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"lotsofsounds": {
"type": "http",
"url": "https://api.lotsofsounds.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://api.lotsofsounds.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain lotsofsounds.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A public, no-key API for searching and previewing curated free sound effects. Built for apps, games, videos, automation, and AI agents by Lots of Sounds.
Looking for a maintained Freesound API alternative? Start with the free sample endpoint below, then use the full Lots of Sounds API when you need catalog search, filters, and downloads.
curl -G "https://api.lotsofsounds.com/api/v1/sounds/sample" \
--data-urlencode "q=door knock" \ --data-urlencode "limit=6"
No account or API key is required. The response contains up to 12 curated samples:
{
"data": [ { "id": "fs-133889", "name": "Large Wood Door Knocking", "description": "Knocking on a door to a large entry", "tags": ["door", "knocking", "wood"], "duration": 2.86766, "stream_url": "/api/v1/sounds/sample/fs-133889/stream" } ], "pagination": { "page": 1, "limit": 6, "total": 6, "totalPages": 1 } }
The example is abbreviated; fields and matching results can change as the curated sample set improves.
| Method | Endpoint | Authentication | Purpose |
|---|---|---|---|
GET | /api/v1/sounds/sample | None | List or search curated samples |
GET | /api/v1/sounds/sample/{id}/stream | None | Get a temporary stream URL |
Use q for a text query or tags for comma-separated tags. limit accepts 1 through 12.
curl -G "https://api.lotsofsounds.com/api/v1/sounds/sample" \
--data-urlencode "tags=door,knock" \ --data-urlencode "limit=6"
Use the relative stream_url returned with a sound:
curl "https://api.lotsofsounds.com/api/v1/sounds/sample/fs-133889/stream"
This returns JSON containing a time-limited stream_url; it does not put an MP3 in this repository.
Requires Node.js 18 or newer.
const params = new URLSearchParams({ q: "notification", limit: "6" });
const response = await fetch( https://api.lotsofsounds.com/api/v1/sounds/sample?${params}, );
if (!response.ok) { throw new Error(Lots of Sounds returned HTTP ${response.status}); }
const { data } = await response.json(); console.log(data);
Run the complete dependency-free example:
node examples/javascript.mjs "notification"
For a typed client that also supports authenticated search, metadata, and downloads, see lotsofsounds/sound-effects-api-js.
The included example uses only the Python standard library:
git clone https://github.com/lotsofsounds/free-sound-effects-api.git
cd free-sound-effects-api python3 examples/python.py "notification"
Or use requests directly:
import requests
response = requests.get( "https://api.lotsofsounds.com/api/v1/sounds/sample", params={"q": "notification", "limit": 6}, timeout=20, ) response.raise_for_status() print(response.json()["data"])
This repository includes a dependency-free find-free-sound-effects skill. Copy that directory into your agent's skills directory, or point your agent at the checked-out repository.
Example request:
Find a short, calm notification sound for an AI assistant.
The skill searches the free endpoint, compares metadata, and requests a temporary stream URL for the selected sample.
Lots of Sounds also provides a hosted Model Context Protocol server:
claude mcp add lotsofsounds --transport http https://api.lotsofsounds.com/mcp
The browse_samples MCP tool works without authentication. Full-catalog tools require an API key:
claude mcp add lotsofsounds --transport http https://api.lotsofsounds.com/mcp \
--header "x-api-key: $LOS_API_KEY"
Cursor, ChatGPT, Claude Desktop, Windsurf, and other Streamable HTTP clients can connect to the same endpoint. See the MCP setup guide for client-specific configuration.
The public samples are intentionally small and curated. The authenticated API adds:
curl -G "https://api.lotsofsounds.com/api/v1/sounds" \
-H "x-api-key: $LOS_API_KEY" \ --data-urlencode "q=gentle notification chime" \ --data-urlencode "max_duration=2"
Read the API docs, compare plans, or sign up and create an API key.
Keep API keys on the server. Do not expose LOS_API_KEY in browser bundles or public repositories.
Both services help developers find sound effects, but this project is not a drop-in implementation of the Freesound API. Lots of Sounds provides a smaller no-key CC0 sample surface, a first-party hosted MCP server for AI agents, and an authenticated API for production search and downloads. Expect different endpoints, response shapes, catalog coverage, and account terms.
Yes. The sample list and sample stream endpoints need no account and no API key. Full-catalog search and downloads require a paid Lots of Sounds plan.
The curated sample collection is CC0. For the full catalog and current usage terms, review the Lots of Sounds license information before publishing audio.
Yes. The REST API returns structured JSON, the repository includes an agent skill, and the hosted MCP server exposes purpose-built sound tools.
No. It contains documentation, small code examples, and an agent skill. Audio is served by the Lots of Sounds API.
Repository code is available under the MIT License. Audio returned by the API is governed separately by the Lots of Sounds license terms.