lescribeaudio-mcp
Registry code: 841ef6d156533ae5
Serveur MCP officiel Le Scribe Audio (stockage France OVHcloud AES-256). Utilisez list_transcriptions ou search_transcriptions pour identifier un file_id, puis get_transcription_text, get_transcription_summary, rename_speaker_label ou get_export_urls.
- endpoint
- https://lescribeaudio.com/api/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is lescribeaudio-mcp live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
- Is lescribeaudio-mcp free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does lescribeaudio-mcp have?
- 6 tools: get_transcription_summary, get_export_urls, search_transcriptions, rename_speaker_label, list_transcriptions, get_transcription_text.
- Is lescribeaudio-mcp safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 6 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
get_transcription_summary auth-required 1h ago
Récupère la synthèse structurée (synthèse exécutive suivie du développement chrono-thématique) associée à une transcription si elle a été générée.
{ "type": "object", "required": [ "file_id" ], "properties": { "file_id": { "type": "string", "description": "Identifiant unique de la transcription." } }, "additionalProperties": false }arguments 13 linesget_export_urls auth-required never probed
Retourne le lien du lecteur interactif Studio et les URLs d'export disponibles (Word .docx 100 % modifiable, PDF, sous-titres .SRT / .VTT, texte brut .TXT, corpus IRaMuTeQ) pour un dossier.
{ "type": "object", "required": [ "file_id" ], "properties": { "file_id": { "type": "string", "description": "Identifiant unique de la transcription." } }, "additionalProperties": false }arguments 13 linessearch_transcriptions auth-required never probed
Recherche un mot-clé, un thème ou un intervenant dans les titres, synthèses et textes déverrouillés des transcriptions de l'utilisateur, avec extraits horodatés.
{ "type": "object", "required": [ "query" ], "properties": { "limit": { "type": "integer", "default": 10, "maximum": 20, "minimum": 1, "description": "Nombre maximal de transcriptions correspondantes à retourner (1 à 20)." }, "query": { "type": "string", "description": "Expression ou mot-clé à rechercher (minimum 2 caractères)." } }, "additionalProperties": false }arguments 20 linesrename_speaker_label auth-required never probed
Renomme globalement l'étiquette d'un intervenant (diarisation) sur toutes ses prises de parole (ex: remplacer 'Intervenant 1' par 'Enquêté P1' ou 'M. Martin') et met à jour les futurs exports Word (.docx).
{ "type": "object", "required": [ "file_id", "old_speaker", "new_speaker" ], "properties": { "file_id": { "type": "string", "description": "Identifiant unique de la transcription." }, "new_speaker": { "type": "string", "description": "Nouveau nom ou code d'intervenant (ex: 'Enquêté P1', 'Mme Dubois')." }, "old_speaker": { "type": "string", "description": "Nom actuel de l'étiquette d'intervenant à remplacer." } }, "additionalProperties": false }arguments 23 lineslist_transcriptions auth-required 1h ago
Liste les transcriptions audio et vidéo du compte Le Scribe Audio authentifié (avec file_id, nom du fichier, durée, statut, date et présence d'une synthèse).
{ "type": "object", "properties": { "limit": { "type": "integer", "default": 20, "maximum": 50, "minimum": 1, "description": "Nombre maximal de dossiers à retourner (1 à 50, défaut 20)." }, "status": { "enum": [ "all", "completed", "processing", "failed" ], "type": "string", "default": "all", "description": "Filtrer par statut ('all', 'completed', 'processing', 'failed')." } }, "additionalProperties": false }arguments 24 linesget_transcription_text auth-required 1h ago
Récupère le texte intégral diarisé (par intervenant, avec timecodes optionnels [HH:MM:SS]) d'une transcription appartenant à l'utilisateur.
{ "type": "object", "required": [ "file_id" ], "properties": { "file_id": { "type": "string", "description": "Identifiant unique de la transcription (issu de list_transcriptions)." }, "max_chars": { "type": "integer", "default": 60000, "maximum": 200000, "minimum": 1000, "description": "Limite de caractères retournés (1000 à 200000, défaut 60000)." }, "offset_chars": { "type": "integer", "default": 0, "minimum": 0, "description": "Décalage en caractères pour lire la suite des très longues séances (défaut 0)." }, "include_timecodes": { "type": "boolean", "default": true, "description": "Inclure les horodatages [HH:MM:SS] devant chaque prise de parole." } }, "additionalProperties": false }arguments 31 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id841ef6d156533ae5.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/841ef6d156533ae5/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/841ef6d156533ae5?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.