- VectorFast Render
- ChatGPT setup
VectorFast Render and ChatGPT
Not yet. ChatGPT connects to custom MCP servers that use OAuth or no authentication, on Business and Enterprise/Edu workspaces. VectorFast Render accepts API keys until its OAuth support ships, so use Claude, Cursor, or the REST API for now.
Not supported yet. Not yet. ChatGPT connects to custom MCP servers that use OAuth or no authentication, and OpenAI's documentation says it cannot present custom API keys. VectorFast Render only accepts API keys until OAuth ships, so ChatGPT cannot connect today. Until then, use Claude, Cursor, or the REST API.
VectorFast Render is in early access. Billing is not connected yet, and API keys are issued to waitlist members as access opens. Join the waitlist
Setup
How ChatGPT will connect once OAuth ships
Open Plugins
In ChatGPT on the web, go to Plugins, select the plus button, then Add custom MCP server.
Enter the endpoint
Enter a name and, under Connection, the public HTTPS endpoint https://vectorfast.ai/mcp.
Authenticate
Configure OAuth sign-in, review the risk warning, and create the plugin. This is the step that needs VectorFast Render's OAuth support.
Use it in a chat
Type @ in the prompt box and pick the plugin, then ask for an image.
Tools your agent gets
| Tool | Access | What it does |
|---|---|---|
| List templateslist_templates | Read-only | List the official VectorFast Render templates (launch post, achievement card, invite card, stat card, changelog, quote card, social square, blog/OG cover) and, if any, your custom templates. Returns each template's id, name, summary, supported sizes and a link to its preview page. Use it to pick a template before calling get_template or render. |
| Get template detailsget_template | Read-only | Get one template's parameter schema (JSON Schema), default and supported sizes, preview image and an example params object. Use it after list_templates to learn which params a template accepts before calling preview_render or render. |
| List brand kitslist_brand_kits | Read-only | List the brand kits in your VectorFast account with their id, name, version and whether a logo is set. Use it to find the brand_kit id to pass to render. |
| Get brand kitget_brand_kit | Read-only | Get a brand kit's colors, fonts, logo URLs (SVG and PNG), default radius and spacing. Omit the id to get the default brand kit. Read-only; edit brand kits at vectorfast.ai. |
| Preview a render (watermarked)preview_render | Read-only | Render a watermarked preview of a template with the given params and brand kit. Free and does not spend credits. Returns a preview image URL. Use it to check layout and copy before calling render. |
| Render an imagerender | Renders | Render a template with the given params and brand kit into a PNG, JPEG or WebP image and return its URL. Spends 1 credit per new render (large sizes may cost more); repeating the same template, params and brand kit returns the cached image and spends nothing. Use preview_render first if you want to check the result without spending credits. |
| Get usage and remaining creditsget_usage | Read-only | Get your current plan, credits used and remaining in this billing period, credit-pack balance and when the period resets. Use it when a render fails for lack of credits or before a large batch. |
Three prompts to try
Ana Lima just shipped her 100th render with us. Make a shareable achievement card she can post: "100 renders shipped", one line of congratulations, dated October 2026.
Example image unavailable in this environment.
Template: Achievement card
Make a referral card Ana Lima can send to friends: "Ana invited you to VectorFast Render", code ANA-2026 good until November 30, and a "Claim 100 free renders" button.
Example image unavailable in this environment.
Template: Invite card
Turn this into a square stat card for our Q3 investor update: 1.2M images rendered in Q3, up 38% on Q2. Add a footnote that it counts API and MCP renders.
Example image unavailable in this environment.
Template: Stat card
Good to know
- ChatGPT does not support machine-to-machine OAuth grants or custom API keys for MCP servers, according to OpenAI's Apps SDK authentication guide.
- Custom MCP servers in ChatGPT are web only, not mobile, per OpenAI's Help Center.
- The examples below show what each prompt renders today through Claude, Cursor or the REST API.
Sources
- OpenAI Help Center: Connecting custom MCP servers in ChatGPT · accessed
- OpenAI Apps SDK: Authentication · accessed
- OpenAI Apps SDK: Connect from ChatGPT · accessed
ChatGPT and VectorFast Render FAQ
- Is VectorFast Render in the ChatGPT directory?
- No. It is not listed in any connector directory yet. You add it by URL as a custom MCP server.
- How does it authenticate?
- With a VectorFast Render API key sent as Authorization: Bearer vf_live_…. OAuth sign-in is planned and will replace the pasted key in clients that support it.
- Does every render cost credits?
- Billing is not connected in early access. When it is, a new render costs one credit and repeating the same template, parameters, and brand kit is served from cache for free; previews are always free.