Skip to main content
Glama

extract_frames

Extract key frames from recorded video using scene detection for visual changes or fixed-rate sampling for timed intervals. Choose the mode that fits your analysis needs.

Instructions

Extract key frames or fixed-rate frames from a recorded video.

mode="scene" selects frames around visual changes and uses scene_threshold
to control sensitivity; lower thresholds produce more frames. mode="fixed_fps"
samples at fps and should be used when timing matters more than scene
changes.

max_frames limits output size. When more frames are found than allowed, the
response reports dropped_for_max. inline_images=True returns FastMCP Image
content for clients that can display frames directly.

rotate_degrees applies orientation normalization when a backend produced a
sideways recording. ffmpeg and ffprobe must be available on PATH.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
video_pathYesAbsolute path to the recorded .mov / .mp4.
output_dirYesAbsolute directory to write PNG frames into.
modeNoFrame selection: 'scene' (visual-change keyframes) or 'fixed_fps' (sample at fps).scene
scene_thresholdNoffmpeg scene threshold for mode='scene'. Range 0.0-1.0. Lower = more frames. Default 0.1.
fpsNoSampling rate for mode='fixed_fps'. Ignored when mode='scene'.
max_framesNoUpper bound on returned frames. Excess reported as dropped_for_max. Default 50.
inline_imagesNoWhen true (default), embed PNGs as FastMCP Image content. WARNING: 50 inline PNGs can exhaust LLM context - set false and rely on output_dir paths for long sessions.
rotate_degreesNoApply orientation normalization (0/90/180/270). Use only when the recording came out sideways.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

Discloses behavioral traits beyond schema: max_frames limits and dropped_for_max reporting, inline_images warning about context exhaustion, rotate_degrees normalization, and threshold effect. Lacks error handling info (e.g., missing file).

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?

Concise and well-structured: front-loads main purpose, then explains modes, then other parameters. No redundant sentences.

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?

Given 8 parameters, 2 required, and presence of output schema, the description covers purpose, modes, parameter effects, limitations, and prerequisites. Adequate for the complexity.

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

Parameters5/5

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

Adds significant meaning beyond schema descriptions: explains scene_threshold range and effect, fps ignored for scene mode, inline_images warning. Schema coverage is 100%, but description enhances understanding.

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 clearly states it extracts key frames or fixed-rate frames from a recorded video, with specific verbs and resource. It distinguishes two modes and explains their use cases.

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

Usage Guidelines4/5

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

Provides clear context on when to use each mode (scene vs fixed_fps) and mentions prerequisite (ffmpeg/ffprobe). However, it does not explicitly state when not to use this tool or reference sibling tools like record_and_extract for alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Corvus400/video-capture-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server