Skip to main content
Glama
Sign In
ffmpeg-mcp-server

ffmpeg-mcp-server

by Ashutos1997
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

extract_thumbnail

Capture a still frame from a video at a chosen timestamp, save it as PNG or JPG, and return the file path plus base64 data for vision model inspection.

Instructions

Capture a single still image from a video. Returns the saved image path and inlined base64 image data so vision models can inspect the frame.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "inputPath": "<inputPath>",
      "outputPath": "<outputPath>"
    },
    "name": "extract_thumbnail"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputPathYesPath to the source video file.
timestampNoTimestamp to capture, such as '00:00:05', '10', or 'midpoint' for the middle frame. Default: '00:00:01'.
outputPathYesDestination image path ending in .png or .jpg (e.g. './thumb.png').
resolutionNoOptional scaled size formatted as 'WIDTHxHEIGHT', such as '1280x720'. Defaults to source resolution.
includeBase64NoReturn base64 image data in response for vision models. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.1
    • addedInput schema / properties / resolution / pattern
      Added value: +"^\\d{2,5}x\\d{2,5}$"
    • addedInput schema / properties / timestamp / pattern
      Added value: +"^((\\d{1,2}:)?\\d{1,2}:\\d{1,2}(\\.\\d+)?|\\d+(\\.\\d+)?|midpoint)$"
  2. Changed5 schema fields changedv0.4.2
    • changedInput schema / properties / includeBase64 / description
      Previous value: -"Whether to include base64 image data in response for AI vision (default: true)"New value: +"Return base64 image data in response for vision models. Default: true."
    • changedInput schema / properties / inputPath / description
      Previous value: -"Path to the input video file"New value: +"Path to the source video file."
    • changedInput schema / properties / outputPath / description
      Previous value: -"Destination image file path (e.g. ./thumb.png or ./thumb.jpg)"New value: +"Destination image path ending in .png or .jpg (e.g. './thumb.png')."
    • changedInput schema / properties / resolution / description
      Previous value: -"Optional scaled resolution, e.g. '1280x720' or '640x360'"New value: +"Optional scaled size formatted as 'WIDTHxHEIGHT', such as '1280x720'. Defaults to source resolution."
    • changedInput schema / properties / timestamp / description
      Previous value: -"Timestamp to capture, e.g. '00:00:05', '10' (seconds), or 'midpoint' (calculates exact middle of video). Default: '00:00:01'."New value: +"Timestamp to capture, such as '00:00:05', '10', or 'midpoint' for the middle frame. Default: '00:00:01'."
  3. Changed1 schema field changedv0.3.0
    • addedInput schema / properties / includeBase64
      Added value: +{
+  "description": "Whether to include base64 image data in response for AI vision (default: true)",
+  "type": "boolean"
+}
  4. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden. It discloses the return shape (saved path plus inlined base64), which is useful, but says nothing about failure modes such as a timestamp beyond the video length, whether outputPath is overwritten, or what permissions are needed to read the source video.

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

Conciseness4/5

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

Two short sentences with the core action front-loaded and the return behavior second. Every clause carries information, though the second sentence could have been used to cover failure behavior instead of only the success payload.

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

Completeness4/5

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

There is no output schema and no annotations, but the description explains the return payload, which is the largest gap for a tool of this shape. Remaining gaps concern error and overwrite behavior rather than the core call contract.

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

Parameters3/5

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

Schema description coverage is 100%, so all five parameters including timestamp formats and resolution are already documented in the schema. The description adds no syntax or default information beyond that, so the baseline of 3 applies.

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

Purpose4/5

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

The description states a specific verb and resource: "Capture a single still image from a video." The word "single" implicitly separates it from the sibling extract_keyframes, but it never names that sibling, so the differentiation is left to inference.

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

Usage Guidelines3/5

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

Usage is only implied by the mention that the returned frame lets vision models inspect it. There is no explicit when-to-use guidance, no exclusion, and no pointer to extract_keyframes or extract_audio as alternatives.

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

Deploy Server

Other Tools