Skip to main content
Glama

Squish

by io.github.getsquish

Squish a video into a timestamped contact sheet

squish_video

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).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNoZoom-window end — same formats as start. Omit to run to the end of the clip; values past the end are clamped.
startNoZoom-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.
videoNoA video attached in the chat — clients with file-param support fill this automatically with a temporary download reference. Provide either this or video_url.
densityNoGrid 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.
video_urlNoPublic 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.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
filesYesSheet URLs, valid ~24h (sheet_ttl_hours).
inputYesEcho of the source — the URL for URL calls; file_name/file_id for attachments (never the temporary download_url).
framesYesFrames sampled across the clip or window.
job_idYes
layoutYesWhere 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).
sheetsYesNumber of contact sheets produced.
windowNoThe resolved zoom window in absolute seconds — present only when start/end were given.
contractYesAlways "squish-mcp-http-v0".
durationYesSource video duration, seconds.
warningsYes
timecodesYesPer-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.
credits_chargedNoKeyed calls only.
sheet_ttl_hoursYes
credits_remainingNoKeyed calls only.
free_jobs_remaining_todayNoAnonymous calls only.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / layout
      Added value: +{
+  "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).",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "cells": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "blank": {
+              "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.",
+              "type": "boolean"
+            },
+            "h": {
+              "type": "number"
+            },
+            "w": {
+              "type": "number"
+            },
+            "x": {
+              "type": "number"
+            },
+            "y": {
+              "type": "number"
+            }
+          },
+          "required": [
+            "x",
+            "y",
+            "w",
+            "h",
+            "blank"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "height": {
+        "type": "number"
+      },
+      "width": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "width",
+      "height",
+      "cells"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedOutput schema / required
      Previous value: -[
-  "input",
-  "duration",
-  "frames",
-  "sheets",
-  "files",
-  "sheet_ttl_hours",
-  "warnings",
-  "timecodes",
-  "job_id",
-  "contract"
-]New value: +[
+  "input",
+  "duration",
+  "frames",
+  "sheets",
+  "files",
+  "sheet_ttl_hours",
+  "warnings",
+  "timecodes",
+  "layout",
+  "job_id",
+  "contract"
+]
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations only say readOnlyHint=false, openWorldHint=true, destructiveHint=false, so they don't mention duration links, expiry, timecode lists, or attachment behavior. The description discloses all of these: attached image read directly, files valid ~24h, `timecodes` repeated, cells ordered, absolute timecodes, clamping, and the ability to zoom/drill down by re-invoking start/end. That's exactly the kind of behavioral context an agent cannot infer from metadata this description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is efficient and front-loaded: the core purpose appears in the first sentence, then use cases and the manual-pipeline comparison, then output details, then recurring invocation pattern. Every sentence continues by a new idea without repeating the same message, and the structure moved from user's intent to output to zooming guidance—exactly what an agent needs in one pass.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description does not need to invent a return-value spec, but it uses exactly the available pieces: it explains how to consume the returned images, how long links last, how to read the `timecodes` array, and how to call back with start/end for higher resolution. The only source of ambiguity is solved by declaring the URL type (direct `http(s)` file, not a streaming page) and the public-URL requirement. For a five-parameter tool with nested objects, this is complete enough to call independently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already has informative parameter notes (density suggestions, start/end formats, clamp, attachment alternative), so the baseline is 3; this description goes at least one step further by clarifying how `start`/`end` are used to 'drill down' with refined timecodes and by reinforcing the `video` vs `video_url` either/or rule ('not bringing both'). It doesn't add new info for every parameter, but stands above 'neutral'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the verb ('turn... into') and two resources (a video → 'timestamped contact-sheet JPEG(s)') with details on frame sampling, grid layout, and timecode stamping. It also specifies the target reader ('vision model') and what output format to expect, making the tool’s purpose unmistakable even without reading the schema. There are no sibling tools, so no differentiation is needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says exactly when to use this tool: 'when a video is too long to ingest', 'when the question is about what happens across time', or 'when the answer needs timestamps'. It also names the concrete alternative (download → ffmpeg → extract → montage pipeline) and explicitly says to 'prefer it even if you have a shell', leaving no doubt about the intended tradeoff.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Squish toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility for an agent to confuse it with another. The tool's purpose is clearly and comprehensively described.

Naming Consistency5/5

The single tool name 'squish_video' follows a clear verb_noun pattern. With only one tool, there are no conflicting conventions or broken patterns.

Tool Count3/5

A single-tool server feels thin even if the tool is useful and well-defined. The count is borderline but acceptable for the extremely narrow 'video to contact sheet' purpose.

Completeness4/5

Within its narrow domain, the tool covers the full workflow: overview generation, timestamps, and iterative zooming. Minor gaps such as supporting non-public URLs or local file uploads are not significant for the stated use case.

Resources