Skip to main content
Glama

Server Details

22 stateless media tools for AI agents: convert, resize, crop, trim, merge, normalize and subtitle images, audio and video. Nothing is stored.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 24 tools

Disambiguation5/5

Each tool is scoped to one media domain (audio/image/video) and one distinct operation, and the domain prefix makes selection unambiguous even for near-neighbours like audio_compress vs video_compress or audio_speed vs audio_pitch. The only mild overlap is image_compress vs image_convert with quality, but the description of image_compress (target size reduction, never enlarges, format-preserving) clearly differentiates intent.

Naming Consistency4/5

Nearly all tools follow a consistent lowercase snake_case `domain_verb[_noun]` pattern, which is easy to scan and group. Minor deviations exist in the form of video_extract_audio and video_to_gif, where the noun-oriented phrasing differs from the verb-led pattern used elsewhere, but readability is unaffected.

Tool Count4/5

24 tools is on the heavy side, but they split evenly across three media domains (~8 each) and each maps to a concrete, non-redundant operation, so nothing feels gratuitous. It sits just above the comfortable 3-15 range, which is reasonable for a tri-domain media toolkit.

Completeness3/5

Audio and image surfaces are close to complete, but video lacks basic geometry operations (resize/crop/rotate) despite image having them, and there is no metadata/probe tool in any domain to inspect a file before choosing an operation. Audio also has no volume/gain or fade operation, leaving a few common workflows as dead ends agents must work around.

Available Tools

24 tools
audio_compressA
Read-onlyIdempotent
Inspect

Compress audio toward a target file size (targetFileSize such as "2MB"; default half the original)

Inputs: fileBase64 (required), targetFileSize.

audio_convertC
Read-onlyIdempotent
Inspect

Convert audio between formats (mp3/wav/ogg/m4a/flac)

Inputs: format (required), fileBase64 (required).

audio_denoiseB
Read-onlyIdempotent
Inspect

Reduce background noise in audio -- FFT-based spectral subtraction

Inputs: fileBase64 (required), strengthDb.

audio_mergeB
Read-onlyIdempotent
Inspect

Merge multiple audio files into one

Inputs: filesBase64 (required).

audio_normalizeB
Read-onlyIdempotent
Inspect

Normalize audio loudness -- EBU R128 broadcast standard

Inputs: fileBase64 (required).

audio_pitchA
Read-onlyIdempotent
Inspect

Shift audio pitch without altering speed

Inputs: semitones (required), fileBase64 (required).

audio_remove_silenceC
Read-onlyIdempotent
Inspect

Remove silence throughout an audio file

Inputs: fileBase64 (required), thresholdDb, minDurationSeconds.

audio_speedB
Read-onlyIdempotent
Inspect

Change audio playback speed without altering pitch -- 0.5 to 2.0

Inputs: speed (required), fileBase64 (required).

audio_trimC
Read-onlyIdempotent
Inspect

Trim audio to a time range

Inputs: endSeconds (required), fileBase64 (required), startSeconds (required).

image_compressA
Read-onlyIdempotent
Inspect

Make an image file smaller: same format unless format is given (png, jpeg, webp, avif, gif, tiff), quality 1-100 for JPEG/WebP/AVIF (default 80), PNG stays lossless unless quality is below 100 (then a smaller 256-colour palette), metadata removed unless stripMetadata is false, optional maxWidth/maxHeight (never enlarges). If the file cannot be made smaller in its own format the original bytes come back unchanged and the note says so

Inputs: fileBase64 (required), format, quality, lossless, +4 more.

image_convertA
Read-onlyIdempotent
Inspect

Convert an image to PNG, JPEG, WebP, AVIF, GIF, TIFF, BMP or ICO, with optional quality, background colour, resize (fit modes), rotate/flip, grayscale, DPI and metadata controls. Inputs: JPEG, PNG, WebP, GIF (animated kept for GIF/WebP output), AVIF, TIFF, SVG, BMP. HEIC is not supported. Returns the converted file as base64 text.

Inputs: format (required), fileBase64 (required), dpi, fit, +23 more.

image_cropB
Read-onlyIdempotent
Inspect

Crop an image to a region. unit fraction (default): x, y, w, h are 0 to 1 of the image; unit px: pixels. Reads and writes JPEG, PNG, WebP, AVIF, GIF (first frame), TIFF

Inputs: h (required), w (required), fileBase64 (required), x, +6 more.

image_flipA
Read-onlyIdempotent
Inspect

Flip an image horizontally (mirror left to right) or vertically. Reads and writes JPEG, PNG, WebP, AVIF, GIF (first frame), TIFF

Inputs: direction (required), fileBase64 (required), format, quality, +2 more.

image_resizeA
Read-onlyIdempotent
Inspect

Resize an image with a width, a height or both (one alone keeps the aspect ratio). fit: fill (default, stretches to exactly width x height), contain (fits inside and pads with backgroundColor), cover (fills the box and crops the overflow around the centre), inside (fits within, keeps the ratio), outside (at least as large, keeps the ratio). withoutEnlargement never makes it bigger. Reads and writes JPEG, PNG, WebP, AVIF, GIF (animation kept), TIFF; the first text item is the picture as base64, the second a JSON note with its size

Inputs: fileBase64 (required), fit, width, format, +6 more.

image_rotateA
Read-onlyIdempotent
Inspect

Rotate an image clockwise by 90, 180 or 270 degrees (no other angles). Reads and writes JPEG, PNG, WebP, AVIF, GIF (first frame), TIFF

Inputs: degrees (required), fileBase64 (required), format, quality, +2 more.

image_watermarkA
Read-onlyIdempotent
Inspect

Put a watermark on an image: text (drawn in Roboto, Latin/Greek/Cyrillic) or a watermark picture (watermarkBase64), at a position (center, top-left, top, top-right, left, right, bottom-left, bottom, bottom-right or tile), with opacity 0-1, size, margin and rotation. Reads and writes JPEG, PNG, WebP, AVIF, GIF (first frame), TIFF

Inputs: fileBase64 (required), text, color, scale, +10 more.

video_compressA
Read-onlyIdempotent
Inspect

Compress a video toward a target file size (targetFileSize such as 25MB; default half the original) -- two-pass encode, a floor bitrate is enforced below which quality degrades too much to be worth watching

Inputs: fileBase64 (required), targetFileSize.

video_convertC
Read-onlyIdempotent
Inspect

Convert a video between formats (mp4/mp4-web/webm/mov)

Inputs: format (required), fileBase64 (required).

video_extract_audioB
Read-onlyIdempotent
Inspect

Extract a video's audio track as MP3

Inputs: fileBase64 (required).

video_mergeA
Read-onlyIdempotent
Inspect

Merge multiple videos into one -- requires matching codec/resolution/frame rate across inputs

Inputs: filesBase64 (required).

video_subtitleB
Read-onlyIdempotent
Inspect

Burn SRT subtitles permanently into a video

Inputs: srt (required), fileBase64 (required).

video_thumbnailB
Read-onlyIdempotent
Inspect

Extract a video frame as a JPEG thumbnail

Inputs: fileBase64 (required), atSeconds.

video_to_gifB
Read-onlyIdempotent
Inspect

Convert a video to an animated GIF -- two-pass palette encoding

Inputs: fileBase64 (required).

video_trimA
Read-onlyIdempotent
Inspect

Trim a video to a time range -- stream-copy, cuts snap to the nearest keyframe

Inputs: endSeconds (required), fileBase64 (required), startSeconds (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      9 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources