{
  "markdown": "# aicut MCP server\n\nGenerate AI **story episodes, videos, images and audio** straight from Claude, Claude Code, or any MCP client - no API key, no dashboard round-trip.\n\n- **Server URL:** `https://mcp.aicut.pro/mcp`\n- **Transport:** Streamable HTTP\n- **Auth:** OAuth 2.1 with dynamic client registration + PKCE. You sign in with your normal aicut account and approve once.\n- **Setup page:** https://www.aicut.pro/mcp\n\nThis repository is the public metadata for the hosted server: there is nothing to install and nothing to run locally.\n\n## Install\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http aicut https://mcp.aicut.pro/mcp\n```\n\nThen run `/mcp`, pick `aicut`, choose **Authenticate**, and approve in the browser tab that opens.\n\n### Claude (web and desktop)\n\nSettings -> Customize -> Connectors -> **Add** -> **Add custom connector**, name it `aicut`, paste `https://mcp.aicut.pro/mcp`, hit **Connect** and approve.\n\n### Any other MCP client\n\nPoint it at `https://mcp.aicut.pro/mcp` over Streamable HTTP. Clients that implement the MCP OAuth flow register themselves; clients with no browser can use an aicut API key as a bearer token instead (keys are issued by hand - email support@aicut.pro).\n\n## Tools\n\n50 tools. Read tools are annotated `readOnlyHint`; the tools that spend carry `destructiveHint` and\n`idempotentHint: false`, so a client asks before spending. Every `generate_*` tool takes\n`estimate_only: true` to price a request without creating anything - and on audio that is the only\nreliable quote, because audio models publish a per-character or per-second RATE rather than a price\ntable. Generations spend tokens from the connected aicut account at the same prices as the app, and\nland in that account's library.\n\n### Catalog and account\n\n| Tool | What it does |\n| --- | --- |\n| `list_models` | The curated video, image and audio catalog with the exact cost of every settings combination. Call this first - model ids and their accepted values cannot be guessed. Searchable and paged. |\n| `get_balance` | Tokens left on the account, and its plan tier. |\n| `list_voices` | The whole voice catalogue - ElevenLabs (stock, plus this account's cloned and custom voices), OpenAI and Amazon Polly in one shape, each with a verdict on what it can be used for. Paged. |\n| `list_characters` | The account's uploaded characters and generated story cast members, in one list. |\n| `list_series` | The AI Video Story catalog: which series (niches) an episode can be made in, with their episode-length ladder, model defaults and prices. |\n| `list_series_ideas` | One series' curated episode ideas. |\n| `browse_series` | Puts the series catalog on screen as a grid of covers whose demo clips play in place, on clients that render cards. Tapping selects, one Confirm writes the pick. |\n\n### Video, image and audio\n\n| Tool | What it does |\n| --- | --- |\n| `generate_video` | Starts a video generation. Asynchronous: returns a job id. |\n| `get_video` | One video by id, with its status and finished url. |\n| `list_videos` | The account's recent videos, paginated. |\n| `delete_video` | Deletes one of the caller's own videos. No refund. |\n| `generate_image` | Generates an image, and usually returns it finished in the same call. |\n| `get_image` | One image by id. |\n| `list_images` | Recent images, paginated. |\n| `generate_audio` | Speech, music or a sound effect, chosen by `model`. |\n| `get_audio` | One audio job by id. |\n| `list_audio` | Recent audio, paginated. |\n| `wait_for_generation` | The long poll: waits server-side and answers whether a job is terminal. |\n| `show_generation` | Replays an earlier generation the user asks to see again. |\n\n### Transforms - working from media you already have\n\nWhat the server measures IS the price: a clip's length, a picture's dimensions, an audio's length.\nMedia the server cannot measure is refused before anything is charged rather than charged and then\nfailed.\n\n| Tool | What it does |\n| --- | --- |\n| `upscale_video` | 2x or 4x an existing video. |\n| `upscale_image` | More pixels in an existing image, from three upscalers: a general-purpose one, one that goes to 10x and is priced per output megapixel, and a creative one that repaints detail as it enlarges. Priced from the picture's measured dimensions. |\n| `extend_video` | Continues an existing video by a chosen number of seconds. |\n| `motion_control` | A character picture plus a reference clip, and the character performs that clip's motion. The reference clip's length is the price. |\n| `generate_lipsync` | A character picture plus audio generated on this account, and the character speaks or sings it, lip-synced. The result is exactly as long as the audio, and the audio's measured length is the price. |\n\n### Video analysis\n\n| Tool | What it does |\n| --- | --- |\n| `analyze_video` | Reads an existing video instead of making one. Spends no tokens; capped per account per day. |\n| `get_analysis` | One analysis by id. |\n| `list_analyses` | Recent analyses, paginated. |\n\n### AI Video Story - the staged episode flow\n\nAn episode is made in stages, and each stage has its own price, so nothing large is bought in one\nblind step: the cast is written free and its portraits are bought; the episode's start frames are\ncharged and PARK for review; firing buys the scene videos; rendering buys the final file.\n\n| Tool | What it does |\n| --- | --- |\n| `generate_cast` | FREE. Writes a story cast for a series and returns it to read. Mints nothing. |\n| `generate_cast_portraits` | Buys one image per cast member and saves the roster to the library. |\n| `regenerate_cast_portrait` | Redraws one cast member's face. |\n| `describe_cast_member` | Changes what one cast member is, then redraws them. |\n| `generate_story_video` | Stage 1: writes the episode, generates the start frames, and parks for review. `estimate_only` quotes the whole episode with its stage split. |\n| `regenerate_story_frame` | Redraws one parked start frame. |\n| `change_story_scene` | Changes what happens in one parked scene, then redraws its frame. |\n| `set_scene_kept` | FREE. Removes a parked scene, so its video is never generated and never charged. |\n| `fire_story_video` | Stage 2: generates the scene videos for the scenes you kept. Irreversible, and an episode cannot fire twice. |\n| `render_story_video` | Stage 3: the final render. Free-tier renders carry a watermark. |\n\n### One-call formats\n\nThese two write and render in a single call: no fire step, no render step.\n\n| Tool | What it does |\n| --- | --- |\n| `generate_fake_text_video` | The fake-text chat-story format. The agent writes the message script; the server speaks it, measures the bubbles and renders it. The voice provider moves the price, so re-quote after changing it. |\n| `generate_image_story` | The AI image story format. The agent writes the narration; the server segments it, writes the image prompts, generates every scene image, speaks it and renders it. Price is driven by the image count. |\n| `list_image_story_styles` | aicut's authored image-story looks. Optional on a create, and picking one forces the pricier edit-capable image model - re-quote after adding one. |\n\n### Publishing to social\n\n| Tool | What it does |\n| --- | --- |\n| `list_social_accounts` | The TikTok, YouTube and Instagram accounts this user has connected. An empty list means they must connect one in a browser - this API cannot. |\n| `prepare_post` | Stages a post of one of the account's finished videos, named by aicut id. Publishes nothing, and expires after 30 minutes. |\n| `review_post` | The consent card: shows the actual video, the destination account and the caption, visibility and disclosure controls, and re-stages the person's own choices. Publishes nothing. |\n| `publish_post` | IRREVERSIBLE: sends or schedules the prepared post. States the per-account rate ceiling rather than making an agent discover it. |\n| `get_post_status` | What the platform says happened, from `prepared` through to `posted` or `failed`. |\n\n### Trends\n\n| Tool | What it does |\n| --- | --- |\n| `list_trends` | aicut's published trend feed. Read-only. |\n| `get_recreate_brief` | How to recreate one trending video. Names the niche it can prove, and deliberately names no series. |\n\n### Uploads - using your own footage and images\n\n| Tool | What it does |\n| --- | --- |\n| `upload_media_widget` | The in-card file picker. The person chooses a file, the card uploads and confirms it, and posts the finished url back. The agent's whole job is to call this and wait. |\n| `upload_media` | A signed upload target for a file on the user's own machine, plus the curl that fills it. |\n| `confirm_upload` | The second half: re-reads the uploaded object, checks its magic bytes against the declared type and measures a video, refusing anything that fails. |\n\n## Docs and policies\n\n- Setup and FAQ: https://www.aicut.pro/mcp\n- Privacy policy: https://www.aicut.pro/privacy\n- Terms: https://www.aicut.pro/terms\n- Support: support@aicut.pro\n",
  "bytes": 8960,
  "sha": "e9b572d9646302d46a9c08352d2fad2bf92488e308b374d606653ff4b9b193f0",
  "repo_slug": "aicut-pro/aicut-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_pro_aicut_aicut_5c166c07/readme"
}