Design

collager.ai

An MCP server for creating photo collages and mosaics in various shapes and styles from user photos, returning previews and status.

1 endpoint5 known toolsFirst detected October 16, 2026Last detected October 16, 2026

ENDPOINT 1

https://collager.ai/mcp

No auth detected

MCP server metadata

Name: collager-ai
Version: 0.1.0

Capabilities

tools

Server instructions

Collager.ai makes photo mosaics and photo collages from people's own photos. - A photo mosaic (one big picture made of hundreds of small photos): call start_photo_mosaic - it gives the link where the user uploads the main photo and the small photos; the site builds a preview in minutes. - A photo collage shaped as a heart, a number, a word or a star: call make_shape_collage with the photos (links, or files the user attached). It answers in seconds with a watermarked preview and a link to get the full-resolution file on collager.ai. - list_collage_shapes shows which shapes exist and how many photos fill each one without repeats.

Known tools 5

make_shape_collage

Builds a photo collage in the shape of a heart, a number (age, anniversary, year), a word, a star, a flower and more from the user's photos, and returns a watermarked preview within seconds.

Inferred read-only

get_shape_collage

Returns the status and the watermarked preview of a collage made with make_shape_collage, by its id (clg_.

Inferred read-only

list_collage_shapes

Lists the shapes make_shape_collage can draw (hearts of 27-164 photos, numbers, words, I love you, circle, star, flower, grid, your own mask) and how many photos fill each without repeats.

Inferred read-only

list_mosaic_styles

Shows the looks of a Collager.

Inferred read-only

start_photo_mosaic

Gives the link where the user builds a photo mosaic: one main photo recreated from many small photos (best with 100-2000 photos - family archive, wedding, team, school year).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.collager-ai]
url = "https://collager.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "collager-ai": {
      "type": "http",
      "url": "https://collager.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: collager-ai
Remote MCP URL: https://collager.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "collager-ai": {
      "url": "https://collager.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "collager-ai": {
      "type": "http",
      "url": "https://collager.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "collager-ai",
  "transport": "streamable-http",
  "url": "https://collager.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.