Search 6,700+ free AI image, video and text prompts and fill them in for your task.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Get the full text of one fillprompt.com prompt by its page URL or slug, with its fill-in slots, sample images or video, and credit to the original author. Fill the slots with the user's details before using the prompt, and keep the credit when you share it.
The prompt page URL from search_prompts (e.g. https://fillprompt.com/prompt/...) or its slug.
Helps when a bare slug is given.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http fillprompt https://fillprompt.com/api/mcp
Get the full text of one fillprompt.com prompt by its page URL or slug, with its fill-in slots, sample images or video, and credit to the original author. Fill the slots with the user's details before using the prompt, and keep the credit when you share it.
| Argument | Type | Description |
|---|---|---|
| ref* | string | The prompt page URL from search_prompts (e.g. https://fillprompt.com/prompt/...) or its slug. |
| type | string | Helps when a bare slug is given. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"ref"
],
"properties": {
"ref": {
"type": "string",
"description": "The prompt page URL from search_prompts (e.g. https://fillprompt.com/prompt/...) or its slug."
},
"type": {
"enum": [
"image",
"video",
"text"
],
"type": "string",
"description": "Helps when a bare slug is given."
}
}
}List the image categories, text prompt types and AI models on fillprompt.com, with how many prompts each has. Use the values with search_prompts.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Search over 6,700 free, ready-to-copy AI prompts on fillprompt.com: image prompts (GPT Image, Nano Banana, Midjourney and more), video prompts (Seedance, Veo, Kling and more) and text prompts (system prompts, agent prompts, roles). Returns titles, page URLs and short previews; call get_prompt for the full text.
| Argument | Type | Description |
|---|---|---|
| type | string | Only image, video or text prompts. |
| limit | integer | How many results to return. |
| model | string | Only prompts written for this AI model, e.g. "Nano Banana", "Seedance", "Claude". See list_filters. |
| query* | string | What the prompt should make, in plain words, e.g. "coffee product photo on marble" or "code review agent". |
| category | string | Image category (e.g. "product-brand", "poster") or text prompt type (e.g. "agent", "developer"). See list_filters. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"query"
],
"properties": {
"type": {
"enum": [
"image",
"video",
"text"
],
"type": "string",
"description": "Only image, video or text prompts."
},
"limit": {
"type": "integer",
"default": 8,
"maximum": 20,
"minimum": 1,
"description": "How many results to return."
},
"model": {
"type": "string",
"description": "Only prompts written for this AI model, e.g. \"Nano Banana\", \"Seedance\", \"Claude\". See list_filters."
},
"query": {
"type": "string",
"description": "What the prompt should make, in plain words, e.g. \"coffee product photo on marble\" or \"code review agent\"."
},
"category": {
"type": "string",
"description": "Image category (e.g. \"product-brand\", \"poster\") or text prompt type (e.g. \"agent\", \"developer\"). See list_filters."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 11, 2026.