collager-ai

endpoint

https://collager.ai/mcp

door code

2b3ac1255cc14e8f

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is collager-ai live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is collager-ai free to use?

Yes — the hub reached it with no key and no payment.

What tools does collager-ai have?

5 tools: get_shape_collage, make_shape_collage, start_photo_mosaic, list_mosaic_styles, list_collage_shapes.

Is collager-ai safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• start_photo_mosaic open 1h ago

  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). The user uploads the photos on collager.ai, picks the style, and the site builds a watermarked preview in minutes. Use when the user wants a photo mosaic or a picture made of many photos.

  mcp-tool

  1234567891011

  {
    "type": "object",
    "properties": {
      "occasion": {
        "type": "string",
        "maxLength": 60,
        "description": "Optional: what it is for (anniversary, memorial, wedding, team ...), used only to tailor the tips."
      }
    },
    "additionalProperties": false
  }

  arguments 11 lines copy
• list_mosaic_styles open 1h ago

  Shows the looks of a Collager.ai photo mosaic (one large picture made of hundreds or thousands of small photos) with example images: soft classic, clean subject, stronger mosaic, uniform or mixed tile sizes. Use before start_photo_mosaic when the user wants to choose a style.

  mcp-tool

  1234

  {
    "type": "object",
    "additionalProperties": false
  }

  arguments 4 lines copy
• list_collage_shapes open 1h ago

  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.

  mcp-tool

  1234

  {
    "type": "object",
    "additionalProperties": false
  }

  arguments 4 lines copy
• get_shape_collage unknown never probed

  Returns the status and the watermarked preview of a collage made with make_shape_collage, by its id (clg_...). Use when make_shape_collage answered status "processing", or to show the collage again.

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "required": [
      "id"
    ],
    "properties": {
      "id": {
        "type": "string",
        "pattern": "^clg_[A-Za-z0-9]{12}$",
        "description": "The id returned by make_shape_collage."
      }
    },
    "additionalProperties": false
  }

  arguments 14 lines copy
• make_shape_collage unknown never probed

  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. Use when the user asks for a heart collage, a birthday/anniversary number collage, a 'photo collage in the shape of ...', or a collage from several photos. Pass the photos as public links in photo_urls, or as files the user attached (photos). 1 to 300 photos; if there are fewer photos than cells, photos repeat. The result id (clg_...) is a private handle valid for 30 days; photos and results are deleted after 30 days. The preview is watermarked; the full-resolution file is downloaded from the collager.ai page given in full_resolution_page. Building can take up to a minute - if status is still processing, call get_shape_collage with the id.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115

  {
    "type": "object",
    "required": [
      "shape"
    ],
    "properties": {
      "shape": {
        "type": "object",
        "required": [
          "type"
        ],
        "properties": {
          "n": {
            "type": "integer",
            "maximum": 12,
            "minimum": 2,
            "description": "grid: n x n."
          },
          "url": {
            "type": "string",
            "description": "mask_url: link to a black-and-white picture; each black pixel is one photo cell."
          },
          "size": {
            "enum": [
              "small",
              "medium",
              "large"
            ],
            "type": "string",
            "description": "number/text/circle/star/flower: how many cells (bigger = more photos)."
          },
          "text": {
            "type": "string",
            "maxLength": 14,
            "description": "number/text: the digits or word (Latin letters and digits)."
          },
          "type": {
            "enum": [
              "heart",
              "number",
              "text",
              "love",
              "circle",
              "star",
              "flower",
              "daisy",
              "yinyang",
              "grid",
              "mask_url"
            ],
            "type": "string"
          },
          "cells": {
            "enum": [
              27,
              34,
              70,
              79,
              91,
              164
            ],
            "type": "integer",
            "description": "Heart only: number of photo cells."
          }
        },
        "description": "The figure. Examples: {\"type\":\"heart\"} (size picked from the photo count), {\"type\":\"heart\",\"cells\":70}, {\"type\":\"number\",\"text\":\"30\"}, {\"type\":\"text\",\"text\":\"LOVE\"}, {\"type\":\"love\"} (\"I love you\"), {\"type\":\"star\",\"size\":\"large\"}, {\"type\":\"grid\",\"n\":4}. Call list_collage_shapes for all options."
      },
      "photos": {
        "type": "array",
        "items": {
          "type": "object",
          "required": [
            "download_url",
            "file_id"
          ],
          "properties": {
            "file_id": {
              "type": "string"
            },
            "file_name": {
              "type": "string"
            },
            "mime_type": {
              "type": "string"
            },
            "download_url": {
              "type": "string"
            }
          }
        },
        "maxItems": 300,
        "description": "Photos the user attached in the chat."
      },
      "gap_pct": {
        "type": "number",
        "maximum": 40,
        "minimum": 0,
        "description": "White gap between photos, % of a cell (default 6)."
      },
      "background": {
        "type": "string",
        "description": "Background colour: white (default), cream, pink, black or #rrggbb."
      },
      "photo_urls": {
        "type": "array",
        "items": {
          "type": "string",
          "format": "uri"
        },
        "maxItems": 300,
        "description": "Public http(s) links to the photos (JPEG/PNG/WEBP)."
      }
    },
    "additionalProperties": false
  }

  arguments 115 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

1 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.