Squish

Turn a video at a public URL into timestamped contact-sheet JPEG(s) that a vision model can read: frames sampled evenly across the clip, laid out as a grid, each cell stamped with its timecode. Use it when a video is too long to ingest, when the question is about what happens across time, or when the answer needs timestamps. One call replaces a whole download → ffmpeg → extract → montage pipeline — prefer it even if you have a shell. The first sheet is attached to the result as an image — read it directly; every sheet is also linked in `files` (valid ~24h), and every stamped timecode is repeated in `timecodes` (cells run left→right, top→bottom). Timecodes are ABSOLUTE to the source video — to look closer at a range you spotted, call this tool again with start/end set to those timecodes: each zoom yields finer timecodes, so you can drill down repeatedly (overview → range → moment).

{
  "type": "object",
  "properties": {
    "video_url": {
      "description": "Public http(s) URL of a video file (anything ffmpeg decodes). Not a YouTube/streaming page — a direct file URL. Provide either this or an attached video, not both.",
      "type": "string"
    },
    "video": {
      "description": "A video attached in the chat — clients with file-param support fill this automatically with a temporary download reference. Provide either this or video_url.",
      "type": "object",
      "properties": {
        "download_url": {
          "type": "string"
        },
        "file_id": {
          "type": "string"
        },
        "mime_type": {
          "type": "string"
        },
        "file_name": {
          "type": "string"
        }
      },
      "required": [
        "download_url",
        "file_id"
      ]
    },
    "density": {
      "description": "Grid density. 3x3 recovers what happened; denser grids (4x4-6x6) recover how it was done. Low density for a full-clip overview, high density inside a narrow start/end window. Default 3x3.",
      "type": "string",
      "enum": [
        "3x3",
        "4x4",
        "5x5",
        "6x6"
      ]
    },
    "start": {
      "description": "Zoom-window start — seconds (67.5) or a timecode as stamped on a sheet (\"1:07\", \"1:07.3\"). Absolute in the source video. Omit to start at 0.",
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "string"
        }
      ]
    },
    "end": {
      "description": "Zoom-window end — same formats as start. Omit to run to the end of the clip; values past the end are clamped.",
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "string"
        }
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

{
  "type": "object",
  "properties": {
    "input": {
      "type": "string",
      "description": "Echo of the source — the URL for URL calls; file_name/file_id for attachments (never the temporary download_url)."
    },
    "duration": {
      "type": "number",
      "description": "Source video duration, seconds."
    },
    "window": {
      "description": "The resolved zoom window in absolute seconds — present only when start/end were given.",
      "type": "object",
      "properties": {
        "start": {
          "type": "number"
        },
        "end": {
          "type": "number"
        }
      },
      "required": [
        "start",
        "end"
      ],
      "additionalProperties": false
    },
    "frames": {
      "type": "number",
      "description": "Frames sampled across the clip or window."
    },
    "sheets": {
      "type": "number",
      "description": "Number of contact sheets produced."
    },
    "files": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Sheet URLs, valid ~24h (sheet_ttl_hours)."
    },
    "sheet_ttl_hours": {
      "type": "number"
    },
    "warnings": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "timecodes": {
      "type": "array",
      "items": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "description": "Per-sheet stamped timecodes, cells left→right then top→bottom — mirrors every label burned into the sheets. Absolute to the source video at every zoom depth."
    },
    "layout": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "width": {
            "type": "number"
          },
          "height": {
            "type": "number"
          },
          "cells": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "x": {
                  "type": "number"
                },
                "y": {
                  "type": "number"
                },
                "w": {
                  "type": "number"
                },
                "h": {
                  "type": "number"
                },
                "blank": {
                  "type": "boolean",
                  "description": "True when that frame could not be read and the cell was left black. Present on EVERY cell — a missing field means a server older than this contract, not a healthy sheet. Blankness is NOT detectable from the image: every cell is painted black before drawing, so a night shot or a cut to black is pixel-identical to a failed read."
                }
              },
              "required": [
                "x",
                "y",
                "w",
                "h",
                "blank"
              ],
              "additionalProperties": false
            }
          }
        },
        "required": [
          "width",
          "height",
          "cells"
        ],
        "additionalProperties": false
      },
      "description": "Where each cell sits on each sheet, in sheet pixels — same order as files, index-aligned with timecodes (cells[n] is the frame stamped timecodes[n]). Published because it cannot be derived: gutters, an outer margin and the branding band mean the grid does not fill the image, so dividing width/height by columns and rows is wrong. Crop by these rectangles to show a single frame. IMPORTANT: these describe the full-resolution sheets at files[], NOT the inline image block — that preview is re-encoded down a size ladder to fit the result budget, so it is often smaller. To crop the inline preview instead, scale every rectangle by (its decoded width / layout[0].width)."
    },
    "job_id": {
      "type": "string"
    },
    "credits_charged": {
      "description": "Keyed calls only.",
      "type": "number"
    },
    "credits_remaining": {
      "description": "Keyed calls only.",
      "type": "number"
    },
    "free_jobs_remaining_today": {
      "description": "Anonymous calls only.",
      "type": "number"
    },
    "contract": {
      "type": "string",
      "description": "Always \"squish-mcp-http-v0\"."
    }
  },
  "required": [
    "input",
    "duration",
    "frames",
    "sheets",
    "files",
    "sheet_ttl_hours",
    "warnings",
    "timecodes",
    "layout",
    "job_id",
    "contract"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}