Skip to main content
Glama
aiexp1

Tanod MCP server

imagepeek: extract an image's dominant colours

image_colors
Read-onlyIdempotent

Extract an image's dominant colours and palette of up to 10 hex, RGB, and share values from a URL or base64 input, with average colour and luminance.

Instructions

imagepeek: Extract the dominant colours of an image. For a placeholder string use image_blurhash. Returns an image's palette of k colours (hex, rgb, share), the dominant one and the average colour with its luminance, from a 200 px sample (median cut refined by k-means; transparent pixels ignored). Reads PNG, JPEG, WebP, GIF, TIFF, BMP, ICO and AVIF; other formats and images over 40 megapixels are refused (not charged). Images are never logged or stored. Typically 0.5-2 s. Price: USD 0.002. Free: 3 imagepeek calls per IP per UTC day. Docs: https://tanod.dev/learn/image-color-palette-api.html

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kNoPalette size (1-10, default 5).
urlNoPublic http(s) URL of the image (at most 10 MB; private, internal and IP-literal hosts are refused); or use image_base64.
auto_orientNoApply the EXIF orientation first (default true).
image_base64NoThe 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
NameRequiredDescriptionDefault
errorNoOnly on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
inputNo
notesNo
sourceNo
averageNo
paletteNo
dominantNo
final_urlNo
operationNo
source_urlNo
pixels_sampledNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive. The description adds substantial behavioral context: return payload shape, sampling method, supported formats, size-limit refusal, privacy (never logged/stored), latency, price, and free-tier quota.

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?

The description is front-loaded with purpose and alternative, followed by return details, format support, privacy, speed, and pricing. Every clause carries operational information useful for invocation, and there is no filler beyond the service prefix.

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 the 4-param schema, full schema description coverage, existing output schema, and annotations covering safety, the description fills all remaining gaps: supported formats, size limits, refusal policy, privacy, latency, cost, and free-tier quota. An agent has everything needed to call correctly.

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 coverage is 100%, so all four parameters are documented in the schema. The description mentions 'k colours' but adds no syntax or constraints beyond the schema's 'Palette size (1-10, default 5)' and does not address auto_orient or the url/base64 choice. With full schema coverage, baseline 3 applies.

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 names the exact operation ('Extract the dominant colours of an image') and immediately routes placeholder-image needs to the sibling image_blurhash. This is a specific verb plus resource that an agent can distinguish from other image tools (metadata, resize, blurhash) without opening schemas.

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?

It gives an explicit alternative for placeholder strings ('use image_blurhash') and states the conditions under which the tool refuses (unsupported formats, over 40 megapixels, not charged). This is clear when-to-use and when-not guidance for the key routing decision.

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