Glif
Easily generate high-quality images, videos and audio using the best available generative models.
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение
Что умеет
- Get Project: Read project state, active job, recent messages, and generated media for a Glif project.
- View Media: Render existing Glif media in the interactive media viewer: once after `get_job_status` completes to display the final gallery, or when the user asks to see, revisit, or pull up media that
- List Projects: List recent Glif projects owned by the authenticated user.
Какие данные видит
Нужен ли аккаунт
Не нужен: сервер работает без входа
Easily generate high-quality images, videos and audio using the best available generative models. Glif is the intelligent, self-optimizing multimedia agent.
Список инструментов сервера (9)
Технические названия из tools/list. Нужны только разработчикам.
| get_project | Read project state, active job, recent messages, and generated media for a Glif project. |
| view_media | Render existing Glif media in the interactive media viewer: once after `get_job_status` completes to display the final gallery, or when the user asks to see, revisit, or pull up media that was already generated (e.g. "show me that capybara again", "open my last image"). It applies after completion, not to `working` polls, and generates nothing (`compose_project` does that). Pass `project_id` to show a project's media, optionally narrowed to specific `asset_ids`. Clients that render media inline show it in the viewer panel, making pasted URLs redundant there; in clients that don't (e.g. CLI hosts), sharing the URLs is how the user gets the media (a sandboxed agent may need its CSP / allowed-domains settings adjusted to load them). |
| list_projects | List recent Glif projects owned by the authenticated user. |
| list_user_skills | List the authenticated user's personal Glif skills. Does not expose global Glif skills. |
| get_user_skill | Fetch one personal Glif skill owned by the authenticated user, including its instructions. Does not expose global Glif skills. |
| compose_project | Create or continue a durable Glif project from natural language. Glif's server-side agent chooses models, tools, and multi-step media workflows. A request that iterates on, refines, animates, or otherwise references anything Glif previously made in this conversation needs the `project_id` from that earlier result — omitting it starts a blank project with no memory of prior media, so omitting `project_id` suits genuinely new, unrelated work. Glif handles batches itself: a series (multiple characters, scenes, variations) works best as one call describing the whole series, kept in one project. Returns immediately with a `jobId` while generation (typically 1–5 minutes) continues in the background: poll `get_job_status` with that jobId every ~5 seconds until status is `completed` or `failed`. The completed poll returns the generated media as resource_link blocks. `view_media` applies after completion, not to `working` polls — called once with `project_id`, it renders the final gallery in UI-capable hosts. In clients with inline rendering, pasted media URLs are redundant; a raw URL is useful only when the client lacks inline rendering or the user asks for one (a sandboxed agent may need its CSP / allowed-domains settings adjusted to load it). |
| get_job_status | Poll a Glif project job started by `compose_project`, using the `job_id` it returned. While the job runs this returns status `working` — wait the returned `pollIntervalSeconds` (currently ~5s) between polls. Once finished it returns the full job result, including the generated media as resource_link blocks. `view_media` applies after completion, not while the job is working — called once with the returned `projectId` as its `project_id`, it renders the final gallery in UI-capable hosts. Job status records expire ~30 minutes after the job finishes; after that, use `get_project` to see the project's media. |
| whoami | Return the authenticated identity, API key label, the MCP surface tag, current subscription/plan, available credit balance, and credits spent over the last 24h / 7d / 30d. Cheap — no agent loop, no generation. |
| upload_file | Upload a file (image, video, audio, or document) and get a CDN URL usable as an attachment/reference for `compose_project`. HOW TO USE: - PUBLIC URL (image/video/audio only) → pass it as `url`. Easiest option; Glif fetches and stores it. Documents can't be uploaded by URL yet — use the local signed flow below. - LOCAL FILE (recommended for any size) → call with `filename` (and/or `kind`) and NO url/base64. Returns a signed curl command that uploads the file directly to the CDN; substitute the file path placeholder, run it, and use the `secure_url` from its JSON response. - LOCAL FILE (tiny, well under 1MB) → pass `base64` with `filename`. - Base64-encoding a real file corrupts it and exceeds tool-call size limits — the signed-curl flow handles any size. |