npm:utilsforagents-mcp

Item: npm:utilsforagents-mcp
Rating: 66
Author: wmcp.sh

https://www.npmjs.com/package/utilsforagents-mcp

66/100 · MCP Trust Grade · checked 3h ago · MCP 1.3.0

What it offers — 9 tools · Finance & Crypto

json-diff

Compare two JSON objects and return a structured diff (RFC 6902 ops, RFC 6901 pointers). ${PRICE} per call.

exif-summary

Extract EXIF metadata from a JPEG image (base64-encoded). ${PRICE} per call.

scrub-metadata

Strip all metadata (EXIF, XMP, ICC, IPTC) from a JPEG or PNG image (base64-encoded). Returns cleaned image as base64. ${PRICE} per call.

html-to-markdown

Convert an HTML string to clean Markdown. ${PRICE} per call.

fetch-markdown

Fetch a URL and convert its HTML content to Markdown. ${PRICE} per call.

fetch-content

Fetch a URL and extract readable text as Markdown. Auto-detects HTML, JSON, Markdown, or plain text. ${PRICE} per call.

url-metadata

Extract page metadata from a URL (title, description, Open Graph, Twitter Card, favicon, feeds, canonical). ${PRICE} per call.

count-tokens

Count tokens in text for LLM input. Uses WASM-based BPE tokenization (exact for OpenAI cl100k_base/o200k_base) or high-fidelity estimation (claude, ge

submit-feedback

Submit short product or feature feedback for UtilsForAgents. Free route, no x402 payment required. Max 600 characters after trimming.

Spec / packaging20%100

✓ depends on an MCP SDK
✓ declares a bin entry (runnable server)
✓ 9 tool(s) detected in source

Security (OWASP MCP)30%25

⚠ references sensitive file paths / env secrets
scanned 1 source file

Maintenance / popularity20%100

published within 90 days
6 published versions

Tool hygiene15%70

no TypeScript types
10 runtime deps

Transparency / provenance15%55

no repository link
✓ MIT license
31 weekly downloads

Findings

WARNMCP08 References sensitive file paths / environment secrets.

INFO Static analysis of npm package utilsforagents-mcp@1.3.0 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.

Grade another server

We re-grade npm:utilsforagents-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:utilsforagents-mcp grade D

Share on X Open card image

https://wmcp.sh/mcp/grade/npm%3Autilsforagents-mcp

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade D](https://wmcp.sh/mcp/grade/npm%3Autilsforagents-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Autilsforagents-mcp)

HTML

<a href="https://wmcp.sh/mcp/grade/npm%3Autilsforagents-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3Autilsforagents-mcp/badge.svg" alt="MCP Trust Grade D · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.