AI photo effects and face swap: apply effects, swap and detect faces, check credits.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Your Morfran API key (create one at https://morfran.com/portal).
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.
Apply an AI photo effect to a photo and return the result image URL. Waits up to about 60 seconds. Costs 11 credits (standard) or 29 credits (pro); failed jobs are refunded. The photo must show a real person who agreed to the edit.
Effect slug from list_effects, e.g. 80s-yearbook
Public URL of the input photo (JPEG, PNG or WebP)
standard or pro
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http morfran https://api.morfran.com/mcp \ --header 'X-API-Key: YOUR_X_API_KEY'
Headers
X-API-Key (required): Your Morfran API key (create one at https://morfran.com/portal).Apply an AI photo effect to a photo and return the result image URL. Waits up to about 60 seconds. Costs 11 credits (standard) or 29 credits (pro); failed jobs are refunded. The photo must show a real person who agreed to the edit.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Effect slug from list_effects, e.g. 80s-yearbook |
| quality | string | standard or pro |
| image_url* | string | Public URL of the input photo (JPEG, PNG or WebP) |
{
"type": "object",
"required": [
"slug",
"image_url"
],
"properties": {
"slug": {
"type": "string",
"description": "Effect slug from list_effects, e.g. 80s-yearbook"
},
"quality": {
"type": "string",
"default": "standard",
"description": "standard or pro"
},
"image_url": {
"type": "string",
"description": "Public URL of the input photo (JPEG, PNG or WebP)"
}
}
}Detect faces in a photo with bounding boxes, age range and gender. Costs 1 credit.
| Argument | Type | Description |
|---|---|---|
| image_url* | string | Public URL of the photo |
{
"type": "object",
"required": [
"image_url"
],
"properties": {
"image_url": {
"type": "string",
"description": "Public URL of the photo"
}
}
}Put the face from the source photo onto the largest face in the target photo and return the result image URL. Costs 5 credits; failed jobs are refunded. Only use photos of people who consented.
| Argument | Type | Description |
|---|---|---|
| source_image_url* | string | Public URL of the photo with the face to use |
| target_image_url* | string | Public URL of the photo to put the face on |
{
"type": "object",
"required": [
"source_image_url",
"target_image_url"
],
"properties": {
"source_image_url": {
"type": "string",
"description": "Public URL of the photo with the face to use"
},
"target_image_url": {
"type": "string",
"description": "Public URL of the photo to put the face on"
}
}
}Return the caller's current Morfran credit balance. Free.
No arguments.
{
"type": "object",
"properties": {}
}Get the status and result URL of a photo effect task (for long-running or async jobs).
| Argument | Type | Description |
|---|---|---|
| task_id* | string | task_id returned by apply_effect |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"description": "task_id returned by apply_effect"
}
}
}Get the status and result URL of a face swap task.
| Argument | Type | Description |
|---|---|---|
| task_id* | string | TaskId returned by face_swap |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"description": "TaskId returned by face_swap"
}
}
}List the available AI photo effects (slug, name, category, description, cover image, credit cost). Free.
No arguments.
{
"type": "object",
"properties": {}
}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 21, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.