com.sfxmint/sounds
REMOTE · SFXMINT.COM
Free CC0 sound effects for apps and games: roles, sets, search; downloads need a free API key
Available components
Last scanned (16 hours ago)
Scores higher than 83% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability59
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2960 tokens (~370/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management86
- Stability check failed: schema churn in the 30 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Nov 26 +8
- Tool “generate_sound” rewrote its description, which is the text the model reads security
- “generate_sound” added an optional parameter “sample_rate” cosmetic
- 18 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “search_sounds” rewrote its description, which is the text the model reads security
- Schema quality: 2375 → 2877 ▼ functional
- Server version: 1.12.1 → 1.13.0 functional
- New tool “create_listen_page” functional
- New tool “get_picks” functional
- 15 Nov 26 +2
- The server rewrote its instructions, which are the text every model session reads security
- Tool “get_role_sound” rewrote its description, which is the text the model reads security
- Tool “get_sound_set” rewrote its description, which is the text the model reads security
- Tool “search_sounds” rewrote its description, which is the text the model reads security
- Schema quality: 479 → 395 ▲ functional
- New tool “generate_sound” functional
- New tool “get_generation” functional
- “get_role_sound” reworded the description of “format” cosmetic
- “get_sound_set” reworded the description of “format” cosmetic
- “search_sounds” reworded the description of “format” cosmetic
- 14 Nov 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 25 to 22.
- 13 Nov 26 0
- Tool “get_sound_set” rewrote its description, which is the text the model reads security
- Tool “search_sounds” rewrote its description, which is the text the model reads security
- 10 Nov 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 22.
- 9 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- 8 Nov 26 −5
No change was recorded against any check on this day. Stability & Change Management went from 67 to 33.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://sfxmint.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=sfxmint.com | CN=WE1,O=Google Trust Services,C=US | 30 Oct 2026 | 28 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 9519592fb70f0d0b13c76335df63e800 |
| SANs: sfxmint.com, www.sfxmint.com, *.www.sfxmint.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of sfxmint.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| sfxmint.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=86400 |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | geolocation=(), camera=(), microphone=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://sfxmint.com/mcp | Verified | 200 | |
| http (plaintext) | http://sfxmint.com/mcp | HTTPS enforced | 301 | https://sfxmint.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
create_listen_page ~194
Make a listening page for the user when choosing sounds for several events (a whole app or game): your candidates grouped by event, about three each, your recommendation first. The user opens listen_url, plays each one, picks one per event, can leave a note (“lower”, “shorter”) and presses Done; then call get_picks. Give the user listen_url before downloading anything for those events; if they say “you decide”, download your recommendations instead. Sounds are slugs from search_sounds, get_role_sound or get_sound_set. The page works for 24 hours; with an API key only this key's account reads the picks back. Up to 40 events of 1–5 sounds.
| Name | Type | Req | Description |
|---|---|---|---|
| events | array | yes | One entry per event |
| title | string | – | The project in a few words, shown on the page, e.g. 'Platformer: forest level' |
No output schema declared.
No examples provided.
generate_sound ~422
Make an individual sound effect from a description when the library has nothing suitable (search_sounds has no full match and its closest sounds do not suit). Needs an SFXMint API key on an account with credits: each take costs 2 credits per started 5 seconds (one credit is one library download), charged when it starts, and failed takes are given back. Without a key or credits it answers with buy_url; the user decides whether to buy, an agent never pays. Returns WAV files (16-bit stereo, 44.1 kHz or 48 kHz as sample_rate asks; signed links valid 15 minutes) with SHA-256, MP3 (128 kbps) through the same link with ?format=mp3, and ogg_url; if they are not ready within about 25 seconds, it returns the order id for get_generation. Not CC0: the user may use them in their own projects, commercially, but not redistribute them as standalone sound files or in a sound collection. AI-generated: the user should listen before use.
| Name | Type | Req | Description |
|---|---|---|---|
| duration_s | number | – | Length of each take in seconds; leave it out and SFXMint chooses from the description. Each started 5 seconds costs 2 credits a take. |
| follow | string | – | How closely the takes follow the words: variety (default, for a short description), balanced, or close (for a detailed one); same price |
| loop | boolean | – | Make it loop seamlessly (default false) |
| prompt | string | yes | What should be heard, in plain English (other languages are translated), at most 400 characters: the source, the action, the material, how it starts and ends. Mention only sounds to be heard. |
| sample_rate | number | – | The WAV's sample rate: 44100 (default) or 48000, the rate video and most game engines mix at; 16-bit stereo either way; same price |
| variations | number | – | How many takes (default 2); each is charged |
No output schema declared.
No examples provided.
get_generation ~74
Check a generation started with generate_sound, generate_ambience, generate_music or change_sound: status, kind and fresh download links for the finished takes, including loop_url when a loop was made.
| Name | Type | Req | Description |
|---|---|---|---|
| order_id | string | yes | The order_id returned by generate_sound, generate_ambience, generate_music or change_sound |
No output schema declared.
No examples provided.
get_picks ~151
Read back a listening page's picks (create_listen_page): for each event the sound the user chose, their note, and what downloading it costs today: again (downloaded today), kept (credits keep it), free (within today's free downloads), credit (one of the account's download credits) or short (past both). Takes the API key of the account that made the page. status says whether the user pressed Done; until then ask them to finish on the page. When short is above 0, pass the next message on as it is, pay_url included, and download the rest; never pay yourself.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The page's code from create_listen_page |
No output schema declared.
No examples provided.
get_role_sound ~468
Choose this when the task calls for a sound for a named event or interaction — a button click, purchase success, error beep, level-up, dialogue blip, notification. Pass the role as plain words: role ids (click, success, purchase-success, dialogue-blip, notification…) and common aliases (button click, ka-ching, jump scare, text blip…) are all accepted. Returns a qualified candidate for that role when one satisfies the requested constraints, with MP3 and WAV URLs, 2-3 alternates and the family page for browsing more. Free downloads are WAV or MP3 alike, counted by sound, not format. Download selected files locally and retain originals. Task-permitted processing requires a recipe, output SHA256, renewed file checks and a listening check. Other task-permitted sources or local synthesis may be mixed in. Optional style: crisp (short, bright, dry), soft (darker, gentler), spacious (reverb, longer tail), balanced (default: most typical). For multiple events consider get_sound_set; use search_sounds for a description or a gap. These are task branches, not a fixed sequence. Unknown roles return not_found with the full role list; GET https://sfxmint.com/api/v1/roles lists roles with aliases.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Delivery format the candidate must have (ogg = Ogg Vorbis, only sounds published before 2026-10-14 have it); default MP3 and WAV URLs. |
| loop | boolean | – | Require prepared loop metadata; seam evidence is returned separately. |
| max_duration_ms | number | – | Hard maximum length of the sound in milliseconds: a file may run longer with near-silence after the sound (audible_ms is the sound, duration_ms the file; checks say which was met). |
| role | string | yes | Role id or alias, e.g. 'click', 'button click', 'purchase-success', 'ka-ching', 'error beep', 'level-up', 'dialogue blip', 'notification' |
| style | string | – | Optional. balanced (default) = the family's most typical take; crisp = short, bright, dry; soft = darker, gentler; spacious = reverb, longer tail |
No output schema declared.
No examples provided.
get_sound ~73
Get full metadata for one sound by slug, including download URLs, description and acoustics measured from the WAV (silence before the sound, where it peaks, audible length, attack, tail, brightness, levels, character labels).
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | Sound slug, e.g. 'impact-punch-01' |
No output schema declared.
No examples provided.
get_sound_set ~238
Get a coherent set of sounds for an app or game in one call — one sound per role, with format metadata, hashes and stable download URLs. Use it when the task needs a whole kit; use get_role_sound for one event. Listen to the files in context. Sets include UI styles, game and app scenarios (fantasy-rpg covers spells, combat, loot, quests and level-up), acoustic-drum-kit, animal-calls (15 isolated calls), and dungeon-traps (6 isolated mechanisms). With an API key the answer also has credits: new_sounds (not kept yet) and credits_left on the account; tell the user before downloading more new sounds than credits_left.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | File format for selection and checks (default WAV; WAV and MP3 download free alike; OGG only among sounds published before 2026-10-14). Legacy urls remains MP3; download_urls follows this format. |
| set | string | – | Set id (default ui-crisp). Includes acoustic-drum-kit, animal-calls and dungeon-traps alongside the UI and scenario sets listed in the enum. |
No output schema declared.
No examples provided.
search_sounds ~685
Free-text search over the SFXMint library of free CC0 sound effects. Use it for sound descriptions, additional constraints or gaps left by another tool. Choose get_role_sound for a named event or get_sound_set for multiple events when that fits the task; these are task branches, not a fixed sequence. Hard constraints (duration, loop, format, excluded words) always apply. results hold sounds whose text has every word of the query. When there are none, closest lists the nearest sounds that meet every hard constraint, best first, each with missing_terms: judge them from title and description and let the user listen. library_fit says how well the library covers the request (full, close, weak, none). Returns direct, hotlinkable MP3 and WAV URLs and verified OGG (Vorbis) URLs where available, no attribution required, plus acoustics measured from the WAV (onset_ms, peak_ms, audible_ms, attack_ms, tail_ms, centroid_hz, peak_dbfs, rms_dbfs), envelope (16 equal slices of the file, 0–100) and bands (percent of energy low <250 Hz, mid, high >4 kHz) to tell candidates apart before the user listens, character labels like 'bright · punchy · tight', loop/file-QC status, and score/match as ranking evidence only (role = known role default, exact = all words hit, partial = some words hit, semantic = nearest by meaning). Free downloads are WAV or MP3 alike, counted by sound, not format. A measured one-shot with silence before or after it also has trimmed_mp3_url and trimmed_wav_url: the same sound without that silence, counted as the same sound.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Optional category slug: ui, retro-game, transition, impact, ambience, water, fire-electric, footsteps, door, mechanical, paper-fabric, glass, animal, crowd, cartoon, magic-scifi, horror, feedback, in… |
| format | string | – | Delivery format (ogg = Ogg Vorbis, only sounds published before 2026-10-14 have it); loop=true defaults to WAV when omitted. |
| limit | number | – | Max results (default 10, max 50) |
| loop | boolean | – | Require (true) or exclude (false) a candidate marked with prepared loop metadata; seam evidence is returned separately. |
| max_duration_ms | number | – | Hard maximum length of the sound in milliseconds: a file may run longer with near-silence after the sound (audible_ms is the sound, duration_ms the file; checks say which was met). |
| query | string | yes | Use concise English search terms for the source or event, action and essential audible traits from the user's request or project context: 'door slam', 'soft UI confirmation chime', 'coin pickup'. A s… |
No output schema declared.
No examples provided.
How do I install the com.sfxmint/sounds MCP server?
com.sfxmint/sounds is a hosted endpoint at https://sfxmint.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · sfxmint.com
claude mcp add --transport http com-sfxmint-sounds 'https://sfxmint.com/mcp'
What is the com.sfxmint/sounds MCP server?
com.sfxmint/sounds is an MCP server listed in the public MCP registry as com.sfxmint/sounds. Free CC0 sound effects for apps and games: roles, sets, search; downloads need a free API key. This page covers its hosted endpoint (https://sfxmint.com/mcp).
Is the com.sfxmint/sounds MCP server safe to use?
com.sfxmint/sounds scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the com.sfxmint/sounds MCP server expose?
com.sfxmint/sounds exposes 8 tools: search_sounds, get_role_sound, get_sound, get_sound_set, create_listen_page, and 3 more. Their descriptions and schemas cost roughly 2,305 tokens of context every time the server is loaded.
Does the com.sfxmint/sounds MCP server require authentication?
No. We connected to com.sfxmint/sounds without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the com.sfxmint/sounds MCP server still maintained?
com.sfxmint/sounds is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the com.sfxmint/sounds MCP server?
VerifyMCP ran 13 checks on com.sfxmint/sounds, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.