Tanod MCP server

imagepeek: resize an image

image_resize

Idempotent

Resize an image to a target width, height, or scale factor using fit modes like inside, contain, cover, or fill. Supports PNG, JPEG, WebP, and more.

Instructions

imagepeek: Resize an image. For several sizes in one call use image_thumbnail; for a box or ratio use image_crop. Returns the image resized to width and/or height (or by scale) with fit inside (default), contain (letterboxed on background), cover (centre crop) or fill (stretched), Lanczos by default; never upscaled unless upscale is true (then upscale_prevented says so). Reads PNG, JPEG, WebP, GIF, TIFF, BMP, ICO and AVIF; other formats and images over 40 megapixels are refused (not charged). Output: base64 data_base64, without EXIF, GPS, XMP or IPTC; over 15 MB or 50 megapixels is a 413 (not charged). Images are not logged; a result is kept only with output "url" (24 h). Typically 0.5-2 s. Price: USD 0.002. Free: 3 imagepeek calls per IP per UTC day. Docs: https://tanod.dev/learn/image-resize-api.html

Input Schema

TableJSON Schema

Name	Required	Description	Default
`fit`	No	With width and height: inside (default; fit within, keep aspect), contain (fit within, padded to the exact box), cover (fill the box, centre crop) or fill (stretch).	inside
`url`	No	Public http(s) URL of the image (at most 10 MB; private, internal and IP-literal hosts are refused); or use image_base64.
`scale`	No	Instead of width/height.
`width`	No	Target width in pixels (1-32768); give width, height, both, or scale.
`format`	No	Output format (default: the input's; ICO in, PNG out).
`height`	No	Target height in pixels (1-32768).
`output`	No	base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window.	base64
`quality`	No	Encoder quality 1-100 (lossy formats).
`upscale`	No	Allow output larger than the input.
`lossless`	No	webp output: lossless encoding (default false).
`optimize`	No	png output: maximum (slower) compression (default false).
`resample`	No	Resampling filter: nearest, box, bilinear, hamming, bicubic or lanczos (default).	lanczos
`background`	No	contain padding colour (default transparent / white).
`auto_orient`	No	Apply the EXIF orientation first.
`progressive`	No	jpeg output: progressive encoding (default false).
`image_base64`	No	The image as standard or url-safe base64 (at most 10 MB decoded; a data:image/...;base64, prefix is fine); or use url.

Output Schema

TableJSON Schema

Name	Required	Description
`url`	No
`bytes`	No
`error`	No	Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
`input`	No
`notes`	No
`width`	No
`format`	No
`height`	No
`sha256`	No
`source`	No
`final_url`	No
`operation`	No
`expires_at`	No
`source_url`	No
`data_base64`	No
`content_type`	No
`upscale_prevented`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Oct 15, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Adds a great deal beyond the annotations: no silent upscaling unless upscale is true, refused formats and megapixel caps are not charged, EXIF/GPS/XMP/IPTC are stripped, a 413 over 15 MB/50 MP is not charged, images are not logged, url results are kept 24 h, typical 0.5-2 s latency, and pricing/free-tier limits. This is rich behavioural disclosure; only the fact that some claims (e.g. the upscale_prevented flag) lean on the output schema keeps it from a 5.

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?

Purpose and sibling routing are front-loaded, then limits, output and cost in a single dense paragraph with no filler sentences. It is on the long side for one paragraph, but nearly every clause carries distinct operational information.

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?

For a 16-parameter image transform with an output schema present, the description still supplies the limits, cost, latency, privacy and retention facts an agent needs to call it safely. Nothing essential appears to be missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description goes further by explaining the functional interplay of parameters — sizing via width and/or height versus scale, how fits interact with background, and Lanczos as the default resample — rather than merely restating field descriptions.

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?

States a specific verb and resource and immediately contrasts with the two relevant siblings: 'For several sizes in one call use image_thumbnail; for a box or ratio use image_crop.' An agent can pick this tool over its nearest alternatives without opening any schema.

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?

Explicit routing rules to alternatives plus concrete exclusions ('other formats and images over 40 megapixels are refused'). It also names the input mechanisms (url vs image_base64) and the output modes, so when-to-use and when-not-to-use are both covered.

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

Deploy Server