Skip to main content
Glama

Image Blur API - blur faces, plates or a whole picture

image_blur
Read-onlyIdempotent

Blur a rectangle (given in percent of the image) or the whole image, strength 3-16. Hide plates, names, screens. Runs on our server, files are deleted right after the call, nothing stored. Free: 25 calls/day per IP. Paid: $0.002 per call via x402 at https://radarbg.com/x402/image-blur.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "area": "all",
      "fileName": "sample.png",
      "fileContent": "iVBORw0KGgoAAAANSUhEUgAAAHgAAABQCAIAAABd+SbeAAAA6klEQVR4nO3cQQ2DABAAwdKgg1cFVQIykIOEyqiIisFDKdsQZv6XXDb3vmFa3jeOd//3AlchdEToiNARoSNCR4SOCB0ROiJ0ROiI0BGhI0JHhI4IHRE6InRE6Mi4Z/jznH+0xmk8Xut3gy46InRE6IjQEaEjQkeEjggdEToidEToiNARoSNCR4SOCB0ROiJ0ROiI0BGhI0JHhI4IHRE6InRE6IjQEaEjQkeEjggdEToidEToiNARoSNCR4SOCB0ZPIFtuOiI0BGhI0JHhI4IHRE6InRE6IjQEaEjQkeEjggdEToidEToiNCRDexBBl0OjJSaAAAAAElFTkSuQmCC"
    },
    "name": "image_blur"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoLeft, percent of width (area=box)
yNoTop, percent of height
areaNobox (a rectangle) or allbox
filesNoOr several files: [{fileName, fileContent (base64)}]
widthNoWidth percent
heightNoHeight percent
fileNameNoFile name with extension, e.g. report.pdf
strengthNo3, 6, 10 or 166
fileContentNoThe file as base64 (a data: URI is fine)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / height / minimum
      Added value: +0
    • addedInput schema / properties / width / minimum
      Added value: +0
    • addedInput schema / properties / x / minimum
      Added value: +0
    • addedInput schema / properties / y / minimum
      Added value: +0
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the description's job is to add beyond that — and it does: processing happens server-side, files are deleted right after the call with nothing stored, plus free-tier limits (25 calls/day per IP) and paid pricing ($0.002 via x402). What it omits is the response shape (does it return the blurred bytes/base64, a URL, or just a status), which matters since no output schema exists.

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?

Three tight sentences, front-loaded with the core operation and mode, then privacy guarantees, then cost. Every sentence carries information an agent needs (capability, safety, quota); nothing is redundant padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All 9 parameters are optional with full schema coverage, so input-side completeness is fine. However, with no output schema the description leaves the return value and its encoding unexplained for a file-in/file-out image tool, and it never clarifies how multi-file ('files') and single-file parameters combine or whether the response is one image or many.

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 description coverage is 100%, so the schema already documents x/y/width/height as percentages, area enum, fileName/fileContent base64, and the files array. The description only echoes region-in-percent and strength, with 'strength 3-16' being looser than the schema's enum (3, 6, 10, 16) and adding no meaning about how strength maps to visual result or how 'files' interacts with the single-file parameters. 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?

States a specific verb and resource ('Blur a rectangle ... or the whole image') and names the two operating modes (box region in percent, or entire image), which separates it cleanly from siblings like image_crop, image_watermark, or image_resize. The privacy use cases ('Hide plates, names, screens') further pin down intent.

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

Usage Guidelines3/5

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

Implied usage is clear from 'Hide plates, names, screens', but there is no explicit when-to-use or when-not guidance and no named alternative for related operations (e.g. crop then blur, or redaction vs. compression). Cost and quota are given, which helps an agent decide whether to call it, but selection guidance against siblings is absent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources