Utilsforagents
API provides pay-per-call utilities: JSON diff, EXIF extraction, metadata scrubbing, HTML-to-Markdown, URL fetching via x402 micropayments.
Trust signal
4 of 4 pillars
coverage 100%
Pillars
Signals
Evidence tiers, not an endorsement · trust model v0.1.0 (provisional) · CDP-lane settlement only (D3) · Trust API coming soon
On-chain traction
ERC-8004 agent registry
Not found in the ERC-8004 agent registry. This is the default state — absence is not a negative signal.
Identity & classification
Settlement volume
USDC settled on-chain · monthly
as of Jul 12, 2026
Endpoints(8)
Compare two JSON objects or arrays and get a structured list of differences. Returns RFC 6902-style patch operations (add, remove, replace) with JSON Pointer paths (RFC 6901). Useful for change detection, audit logging, config comparison, and finding what changed between two API responses. Send {"left": <original>, "right": <modified>}. Optional: includeUnchanged (bool) includes unchanged paths; maxDepth (int 1–256, default 64) limits traversal depth.
Fetch a URL and convert its HTML content to Markdown. Handles redirects, downloads the HTML, and returns clean Markdown suitable for LLM context windows or document processing. Use this to read and summarize web pages, documentation, or articles. Send {"url": "https://..."}. Remote fetch timeout: 5s, max download size: 2 MB.
Convert an HTML string to clean Markdown. Strips navigation, scripts, styles, and non-content elements. Use when you have an HTML string in memory and want Markdown for an LLM context window, document processing, or storage. Send {"html": "<html string>"}. Also accepts a raw text/html body. Max 5 MB.
Extract EXIF metadata from a JPEG image. Returns structured fields including camera make/model, GPS coordinates, timestamp, aperture, shutter speed, ISO, and more. Useful for reading location data from photos, auditing camera settings, or checking what metadata is embedded in an image. Send the image as a raw binary body (Content-Type: image/jpeg) or multipart/form-data with field name 'file'. Max 5 MB.
Remove all embedded metadata (EXIF, XMP, IPTC) from a JPEG or PNG image and return the cleaned image binary. Use this to strip GPS coordinates, camera info, author data, and other privacy-sensitive metadata before sharing or publishing images. Send raw binary body (Content-Type: image/jpeg or image/png) or multipart/form-data with field 'file'. Max 5 MB. Returns cleaned binary image with Content-Type matching the original format.
Fetch a URL and return its text content. Auto-detects the format: HTML is converted to Markdown, JSON is returned as formatted text, and Markdown or plain text is returned as-is. Use when you need to read any URL without knowing its content type in advance. Send {"url": "https://..."}. Remote fetch timeout: 5s, max download size: 2 MB.
Fetch a URL and extract structured metadata from its HTML: title, description, canonical URL, language, favicon URL, RSS/Atom feed links, Open Graph tags (og:title, og:image, og:type, og:description, og:url), Twitter Card tags, and other meta tags (author, keywords, robots). Use this to get Open Graph data, preview cards, or site information without parsing HTML yourself. Send {"url": "https://..."}. Remote fetch timeout: 5s, max download size: 2 MB.
Count the number of tokens in a text string using the specified tokenizer encoding. Supports cl100k_base (GPT-4/GPT-3.5, exact BPE), o200k_base (GPT-4o, exact BPE), claude (Claude models, estimated), and gemini (Gemini models, estimated). Use before sending text to an LLM to estimate cost, check context window fit, or enforce token budgets. For base64-encoded images, set content_type='image' for tile-based token estimation. Send {"text": "...", "encoding": "cl100k_base"}. Max 50 MB text.