ai.ccapi/mcp

Est-ce que ai.ccapi/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.ccapi/mcp » est classé « Vérifié ». Aucun comportement malveillant détecté au test comportemental. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 11 outils

• chat_completion≈ 616 tokens

  Send a conversation to any text model available through CCAPI (Claude, GPT, Gemini, DeepSeek, GLM, MiniMax, Kimi, Qwen…) and get the reply. Useful for consulting a second model for a different perspective, running a cheap model over bulk work, or reaching a model the current client does not have configured. Responses are non-streaming.

  Paramètres, retour & exemple (6)

  Paramètres

  • stop · null|array · optionnel
    Up to 4 sequences that stop generation.
  • model · string · requis
    Exact model name, e.g. claude-sonnet-5 or deepseek-v4-pro. Call list_models with category 'text' if unsure.
  • top_p · null|number · optionnel
    Nucleus sampling probability mass, 0-1. Omit for the model default.
  • messages · null|array · requis
    Conversation so far, oldest first. Must contain at least one message.
  • max_tokens · null|integer · optionnel
    Maximum tokens to generate. Omit for the model default.
  • temperature · null|number · optionnel
    Sampling temperature, typically 0-2. Omit for the model default.

  Exemple d'appel

  {"name": "chat_completion", "arguments": {"model": "texte", "messages": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"model": "texte", "usage": {}, "content": "texte", "finish_reason": "texte"}}

• edit_image≈ 822 tokens

  Edit existing images according to an instruction, using the dedicated image edit endpoint. Provide at least one source image. For pure text-to-image, or for models that take references through the generation endpoint, use generate_image instead.

  Paramètres, retour & exemple (11)

  Paramètres

  • n · null|integer · optionnel
    How many images to generate. Defaults to 1. Each one is billed.
  • size · string · optionnel
    Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default.
  • async · boolean · optionnel
    Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'.
  • model · string · requis
    Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure.
  • images · null|array · optionnel
    Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references.
  • prompt · string · requis
    Description of the image to generate.
  • quality · string · optionnel
    Quality hint, e.g. low, medium, high or auto. Model-dependent.
  • aspect_ratio · string · optionnel
    Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16.
  • nsfw_checker · null|boolean · optionnel
    Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved.
  • wait_seconds · null|integer · optionnel
    Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time.
  • response_format · string · optionnel
    'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary.

  Exemple d'appel

  {"name": "edit_image", "arguments": {"model": "texte", "prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "model": "texte", "images": "texte", "status": "texte", "task_id": "texte", "platform": "texte"}}

• extend_music≈ 517 tokens

  Continue an existing song from a given timestamp, producing a longer version. Requires the clip_id of a previously generated song, which appears in the 'raw' payload of a completed generate_music task. Asynchronous — poll with get_task.

  Paramètres, retour & exemple (7)

  Paramètres

  • tags · string · optionnel
    Style tags for the extension.
  • title · string · optionnel
    New title for the extended song.
  • prompt · string · optionnel
    Lyrics for the extended section.
  • clip_id · string · requis
    ID of the song to extend, taken from the 'raw' clip list of a completed generate_music task.
  • provider · string · optionnel
    Music backend: 'suno' (default) or 'producer'.
  • continue_at · number · requis
    Timestamp in seconds within the original song to continue from.
  • wait_seconds · null|integer · optionnel
    Poll server-side for up to this many seconds (max 240).

  Exemple d'appel

  {"name": "extend_music", "arguments": {"clip_id": "texte", "continue_at": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"raw": "texte", "note": "texte", "status": "texte", "task_id": "texte", "platform": "texte", "audio_urls": "texte"}}

• generate_image≈ 836 tokens

  Generate an image from a text prompt, optionally guided by reference images (image-to-image). Returns image URLs directly. Most models finish in 10-60 seconds; if your client times out, set async=true to get a task_id you can poll instead. This call costs money — do not retry speculatively.

  Paramètres, retour & exemple (11)

  Paramètres

  • n · null|integer · optionnel
    How many images to generate. Defaults to 1. Each one is billed.
  • size · string · optionnel
    Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default.
  • async · boolean · optionnel
    Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'.
  • model · string · requis
    Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure.
  • images · null|array · optionnel
    Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references.
  • prompt · string · requis
    Description of the image to generate.
  • quality · string · optionnel
    Quality hint, e.g. low, medium, high or auto. Model-dependent.
  • aspect_ratio · string · optionnel
    Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16.
  • nsfw_checker · null|boolean · optionnel
    Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved.
  • wait_seconds · null|integer · optionnel
    Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time.
  • response_format · string · optionnel
    'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary.

  Exemple d'appel

  {"name": "generate_image", "arguments": {"model": "texte", "prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "model": "texte", "images": "texte", "status": "texte", "task_id": "texte", "platform": "texte"}}

• generate_lyrics≈ 454 tokens

  Write song lyrics from a description, without generating audio. Useful as a first step before generate_music with custom=true, so the user can approve the words before paying for audio. Asynchronous — poll with get_task.

  Paramètres, retour & exemple (4)

  Paramètres

  • prompt · string · requis
    Description of the lyrics to write, e.g. 'a love song about meeting someone at a coffee shop'.
  • provider · string · optionnel
    Music backend: 'suno' (default) or 'producer'.
  • lyrics_model · string · optionnel
    Lyrics model: classic or remi.
  • wait_seconds · null|integer · optionnel
    Poll server-side for up to this many seconds (max 240). Lyrics usually finish in under 30 seconds.

  Exemple d'appel

  {"name": "generate_lyrics", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"raw": "texte", "note": "texte", "status": "texte", "task_id": "texte", "platform": "texte", "audio_urls": "texte"}}

• generate_music≈ 681 tokens

  Generate a song with vocals or instrumental. Two modes: simple (custom=false) where you describe the song and the model writes the lyrics, or custom (custom=true) where you supply lyrics, title and style tags. Asynchronous — returns a task_id you poll with get_task; generation usually takes 30-120 seconds and normally yields two variations.

  Paramètres, retour & exemple (9)

  Paramètres

  • tags · string · optionnel
    Comma-separated style tags, e.g. 'pop, upbeat, guitar'. Max 200 characters.
  • model · string · optionnel
    Suno model version, e.g. chirp-v5 or chirp-v4-5-plus. Omit for the platform default.
  • title · string · optionnel
    Song title. Used in custom mode.
  • custom · boolean · optionnel
    false (default) lets the model write the lyrics from your description; true means prompt contains lyrics you wrote and you should also set title and tags.
  • prompt · string · requis
    In simple mode (custom=false) a description of the song, e.g. 'a dreamy lo-fi track about late-night trains'. In custom mode (custom=true) the actual lyrics, with section markers like [Verse] and [Chorus].
  • provider · string · optionnel
    Music backend: 'suno' (default) or 'producer'.
  • instrumental · boolean · optionnel
    Generate without vocals.
  • wait_seconds · null|integer · optionnel
    Poll server-side for up to this many seconds (max 240) and return finished audio if it completes in time. Omit to return a task_id immediately.
  • negative_tags · string · optionnel
    Styles to avoid, e.g. 'heavy metal, rap'.

  Exemple d'appel

  {"name": "generate_music", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"raw": "texte", "note": "texte", "status": "texte", "task_id": "texte", "platform": "texte", "audio_urls": "texte"}}

• generate_video≈ 849 tokens

  Generate a video from a text prompt, optionally driven by reference images (image-to-video, first/last frame). This is asynchronous: it returns a task_id you poll with get_task(platform='video'). Generation usually takes 30-180 seconds. Pass wait_seconds to have the server poll for you. Video generation is the most expensive capability here — confirm the prompt with the user before spending on retries.

  Paramètres, retour & exemple (11)

  Paramètres

  • model · string · requis
    Exact model name, e.g. doubao-seedance-2-0-260128, veo-3.1-quality or viduq3-pro. Call list_models with category 'video' if unsure.
  • ratio · string · optionnel
    Aspect ratio, e.g. 16:9, 9:16, 1:1, 21:9 or adaptive. Which values a model accepts varies; an unsupported one is rejected with a message naming the valid ones.
  • audios · null|array · optionnel
    Optional Seedance reference audio URLs or asset:// URIs returned by the trusted asset catalog. Reference audio cannot be used alone.
  • images · null|array · optionnel
    Optional reference image URLs. A single image is used as the first frame; use image_roles to control multiple.
  • prompt · string · requis
    Description of the video to generate.
  • videos · null|array · optionnel
    Optional Seedance reference video URLs or asset:// URIs returned by the trusted asset catalog.
  • duration · null|integer · optionnel
    Clip length in seconds. Model-dependent, typically 4-15; an unsupported value is rejected with a message naming the supported ones. Omit for the model default.
  • resolution · string · optionnel
    Output resolution: 480p, 720p (widest compatibility) or 1080p. Model-dependent.
  • image_roles · null|array · optionnel
    Role of each entry in images, positionally: first_frame, last_frame or reference_image.
  • wait_seconds · null|integer · optionnel
    Poll server-side for up to this many seconds (max 240) and return the finished video if it completes in time. Omit to return a task_id immediately.
  • generate_audio · null|boolean · optionnel
    Generate a synchronised soundtrack. Only some models support this.

  Exemple d'appel

  {"name": "generate_video", "arguments": {"model": "texte", "prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "model": "texte", "status": "texte", "task_id": "texte", "platform": "texte", "video_urls": "texte"}}

• get_balance≈ 294 tokens

  Report the remaining and used balance for this CCAPI key. Useful before starting an expensive batch of generations, or to explain a quota failure to the user.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_balance", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "currency": "texte", "unlimited": true, "used_amount": 1, "total_amount": 1, "remaining_amount": 1}}

• get_task≈ 503 tokens

  Check the status of an asynchronous generation task submitted by generate_video, generate_music, generate_lyrics, extend_music, or generate_image with async=true. Pass the platform and task_id exactly as they were returned. Status is one of queued, in_progress, completed or failed; poll every few seconds until it settles, or pass wait_seconds to have the server wait for you.

  Paramètres, retour & exemple (3)

  Paramètres

  • task_id · string · requis
    Task identifier returned by the submit tool.
  • platform · string · requis
    Platform the task belongs to, exactly as returned by the submit tool: image, video, suno or producer.
  • wait_seconds · null|integer · optionnel
    Poll server-side for up to this many seconds (max 240) and return once the task finishes. Omit for a single immediate status check.

  Exemple d'appel

  {"name": "get_task", "arguments": {"task_id": "texte", "platform": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"raw": "texte", "note": "texte", "status": "texte", "task_id": "texte", "platform": "texte", "progress": "texte", "fail_reason": "texte", "result_urls": "texte"}}

• list_models≈ 528 tokens

  List the AI models this CCAPI key can actually call, with their capability category and the MCP tool that drives them. Call this before generating anything if you are unsure a model name is valid — availability depends on the key's group and changes over time. Never guess model names.

  Paramètres, retour & exemple (2)

  Paramètres

  • search · string · optionnel
    Case-insensitive substring match on the model name, e.g. 'claude' or 'seedance'.
  • category · string · optionnel
    Filter by capability. One of: text, image, video, music, embedding, other. Omit to list every model this key can use.

  Exemple d'appel

  {"name": "list_models", "arguments": {"search": "texte", "category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "total": 1, "models": "texte"}}

• upscale_image≈ 485 tokens

  Increase the resolution of an existing image 2x with ccapi-upscale-v1. Input must be between 256x256 and 1024x1024 and under 5 MB; for larger inputs, regenerate with a high-resolution model instead.

  Paramètres, retour & exemple (3)

  Paramètres

  • image · string · requis
    The image to upscale, as an HTTPS URL, data URL, or raw base64. Width and height must each be 256-1024 px and the file at most 5 MB.
  • model_quality · string · optionnel
    Upscale quality hint: HQ, MQ (default) or LQ.
  • response_format · string · optionnel
    'url' (default) or 'b64_json'.

  Exemple d'appel

  {"name": "upscale_image", "arguments": {"image": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "model": "texte", "images": "texte", "status": "texte", "task_id": "texte", "platform": "texte"}}

Badge pour votre README

Ce serveur a passé le pentest comportemental. Le badge porte son nom et renvoie à cette fiche — la preuve, c'est la fiche (verdict live qu'on contrôle), pas l'image.

[![Vérifié par MCP Hub](https://dokore.fr/badge/ai.ccapi--mcp.svg)](https://dokore.fr/serveur/ai.ccapi--mcp)

<a href="https://dokore.fr/serveur/ai.ccapi--mcp"><img src="https://dokore.fr/badge/ai.ccapi--mcp.svg" alt="Vérifié par MCP Hub" height="20"></a>

Réévalué en continu : si le comportement change, le verdict tombe et le badge disparaît. Un badge qui ne pointe pas vers une fiche dokore.fr ne prouve rien. Comment ça marche

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.ccapi.ai/mcp