Glif
Easily generate high-quality images, videos and audio using the best available generative models.
What it can do
- 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.
What data it sees
Do you need an account
No: the server works without sign-in
Easily generate high-quality images, videos and audio using the best available generative models. Glif is the intelligent, self-optimizing multimedia agent.
How to connect
How to connect Glif to Claude
The server address to paste into Claude settings:
https://glif.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Glif to ChatGPT
The server address to paste into ChatGPT settings:
https://glif.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Glif to Cursor
The server address to paste into Cursor settings:
https://glif.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (9)
Raw names from tools/list. Only developers need these.
| 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. |