firstch-tools

A collection of small developer tools available through MCP, a standard way for coding agents to call external tools. It covers tasks involving web content, text, code, data formats, images, security values, and time conversions.

In plain words
What is it for?
Use it for accessibility contrast checks, WebP conversion, JSON-LD and robots.txt creation, formatting, encoding, hashing, JWT checks, QR codes, UUIDs, timestamps, SQL, Markdown tables, and related utilities.
Why use it?
It keeps many routine conversions, checks, and generators in one tool collection instead of requiring separate scripts or websites.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add First-CH/firstch-tools-mcp
agentmods
npx agentmods add plugins/first-ch/firstch-tools-mcp/firstch-tools
Clone the repo
git clone --depth 1 https://github.com/First-CH/firstch-tools-mcp

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

firstch-tools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/firstch-tools/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "firstch-tools",
  "displayName": "First CH Tools",
  "version": "0.26.0",
  "description": "MCP tools for WCAG contrast check, JP character/X-weight count, WebP conversion, JSON-LD generation, llms.txt generation, encoding/line-ending conversion, Marp Markdown→slide rendering, test data generation, text/code diffing, cron-expression explanation, Base64/data-URI encoding, URL parameter editing, HTML entity escaping/unescaping, px ⇄ rem/em unit conversion, HEX/RGB/HSL/OKLCH colour conversion with alpha compositing, MD5/SHA-1/SHA-256/SHA-384/SHA-512 hashing with checksum verification, JWT decoding with expiry and signature checks, User-Agent parsing with browser, engine, OS, device and bot detection, bulk UUID v4 / ULID generation, aspect-ratio calculation with responsive sizing, Markdown table formatting with TSV/CSV conversion, SQL query formatting, QR code generation (SVG / PNG), Unix timestamp ⇄ ISO 8601 / local-time conversion, robots.txt generation with AI-crawler presets, and case conversion (camelCase / snake_case / kebab-case and eight more) — the same logic that powers tools.first-ch.com.",
  "author": {
    "name": "First CH LLC",
    "url": "https://first-ch.com"
  },
  "homepage": "https://tools.first-ch.com",
  "repository": "https://github.com/First-CH/firstch-tools-mcp",
  "license": "MIT"
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 14 lines scan A c7ffa8ec4431

Subscribe to this mod's changes

firstch-tools is a plugin published in the GitHub repository First-CH/firstch-tools-mcp (0 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.