Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

com.yaktool/image

NPM · YAKTOOL-IMAGE-MCP · SCANNED SEP 20

Compress, convert and resize images locally, with marketplace presets and rule rechecks.

Available components

npm · yaktool-image-mcp 76
+4 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 1 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency19
Schema Quality & AI Usability65
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1056 tokens (~528/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the com.yaktool/image MCP server?

com.yaktool/image runs locally as an npm package, launched with npx -y yaktool-image-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · yaktool-image-mcp

# add to Claude Code
claude mcp add com-yaktool-image -- npx -y yaktool-image-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "com-yaktool-image": {
      "command": "npx",
      "args": [
        "-y",
        "yaktool-image-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-yaktool-image": {
      "command": "npx",
      "args": [
        "-y",
        "yaktool-image-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add com-yaktool-image -- npx -y yaktool-image-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-yaktool-image": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "yaktool-image-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-yaktool-image --command npx --arg -y --arg yaktool-image-mcp
# ~/.hermes/config.yaml
mcp_servers:
  com-yaktool-image:
    command: "npx"
    args: ["-y", "yaktool-image-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-yaktool-image": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "yaktool-image-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add com-yaktool-image -t stdio -c npx -a -y yaktool-image-mcp
// mcp.json
{
  "mcpServers": {
    "com-yaktool-image": {
      "command": "npx",
      "args": [
        "-y",
        "yaktool-image-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 5 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/yaktool-image-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 1 package
Packages resolved 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 2 exposed · ~1,056 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compress_image ~465

Compress a local PNG or JPEG file with the same engine as the yaktool web compressor, documented in 12 published behaviours. smart mode (default): PNGs are palette-quantized with an alpha-weighted PSNR floor derived from `quality` (fewest colours that stay above the floor; falls back to lossless when even 256 colours would visibly degrade); JPEGs are re-encoded with mozjpeg, progressive. lossless mode: pixels stay byte-identical — PNGs lose only render-neutral metadata chunks and get an oxipng pass; JPEGs are rebuilt without metadata segments. Optional `format` converts to WebP or AVIF (both support true lossless; AVIF is slowest but smallest). GUARANTEES: the input file is never modified; an existing output file is never overwritten (delete it first if you mean it); if no candidate beats the original size, NO file is written and the result says so (`outcome: "kept-original"`) — the original is already optimal, do not retry with the same settings. Animated PNGs are skipped, never flattened to one frame. Returns { outcome, path, out?, originalBytes, outputBytes?, savedPercent?, report } where report shows the work: colours before/after, measured PSNR dB, metadata removed per segment, encoder used, and why the decision fell the way it did.

NameTypeReqDescription
formatstring–Output format, default "same" (no conversion). webp/avif honour mode: lossy at the mapped quality, or true lossless.
modestring–smart (default) = visually-guarded lossy; lossless = pixels byte-identical, metadata and encoding only.
outstring–Absolute output path. Default: alongside the input as <name>-compressed.<ext> (extension follows `format`). Never overwrites an existing file.
pathstringyesAbsolute path to the PNG or JPEG file to compress.
qualityinteger–0-100, default 60. In smart mode this sets the PNG PSNR floor (30 + q*0.1 dB) and the mozjpeg/WebP/AVIF encoder quality. Ignored in lossless mode.

No output schema declared.

No examples provided.

convert_image ~591

Convert a local image between PNG, JPEG, WebP and AVIF, optionally resizing it, with the same engine as the yaktool web converter (5 documented behaviours). MARKETPLACE PRESETS: pass preset (amazon-main | gmc | ebay) to get that platform's target format and size, and the output is RECHECKED against the platform's published rules — the result carries a per-rule verdict list (recheck.verdicts, rule IDs MED-*/IMG-S01) and recheck.allPass, so you can tell the user whether the file is actually right for the platform, not just converted. RESIZING: fit (default) scales inside the box and never crops; crop fills and centre-crops; pad scales inside and fills with white. A single dimension always scales proportionally. UPSCALING IS REFUSED BY DEFAULT: when the target is larger than the source, the image keeps its size and the result says so (ICV-002) — stretching adds blur, not detail. Pass allowUpscale: true only when the user explicitly accepts that. HONEST BY CONSTRUCTION: animated GIFs are refused rather than flattened (ICV-001); JPEG output composites transparency onto white and says so (ICV-004); metadata (EXIF/GPS) is not carried over and the report says what was dropped (ICV-003). GIF/BMP input is browser-only — this tool takes PNG, JPEG, WebP, AVIF. HEIC is not supported anywhere (LGPL+HEVC patent stack, documented on the web page). GUARANTEES: the input file is never modified; an existing output file is never overwritten. Returns { outcome, path, out?, report{ inputFormat, outputFormat, before{w,h,bytes}, after{w,h,bytes}, resizeApplied?, skippedUpscale?, alphaFlattened?, metadataBytesRemoved?, encoder, findings[], recheck? } }.

NameTypeReqDescription
allowUpscaleboolean–Default false: refuse to scale up, keep the original size and report ICV-002 instead.
fitstring–How to reach an exact width×height: fit (never crop, default), crop (centre-crop), pad (white borders).
heightinteger–Target height in px.
outstring–Absolute output path. Default: alongside the input as <name>-converted.<ext>. Never overwrites an existing file.
pathstringyesAbsolute path to the PNG, JPEG, WebP or AVIF file to convert.
presetstring–Marketplace preset: sets target format and size, and enables the platform recheck.
targetstring–Output format. Defaults to the preset's format, or jpeg when no preset is given.
widthinteger–Target width in px. Overrides the preset size when given.

No output schema declared.

No examples provided.

Common questions

What is the com.yaktool/image MCP server?

com.yaktool/image is an MCP server listed in the public MCP registry as com.yaktool/image. Compress, convert and resize images locally, with marketplace presets and rule rechecks. This page covers its npm package (yaktool-image-mcp).

Is the com.yaktool/image MCP server safe to use?

com.yaktool/image scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the com.yaktool/image MCP server expose?

com.yaktool/image exposes 2 tools: compress_image, convert_image. Their descriptions and schemas cost roughly 1,056 tokens of context every time the server is loaded.

Is the com.yaktool/image MCP server still maintained?

com.yaktool/image is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the com.yaktool/image MCP server under?

com.yaktool/image declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.