QuickHelp

QuickHelp

free dev tools (JWT, JSON, Base64, image converter, hash, UUID, and more) — each with a UI, REST API, and MCP server. No auth, stateless, <5s.

Category
Visit Server

README

quickhelp.dev — 15 free developer tools, each with a UI, API, and MCP server

Every tool runs in your browser, exposes a REST API, and is wired into a single MCP server so AI agents and humans get first-class access without any sign-up.

Live: quickhelp.dev · API: quickhelp.dev/openapi.json · MCP: quickhelp.dev/mcp


Tools

Tool UI API endpoint
JWT Decoder /jwt-decoder POST /api/jwt-decoder
JSON Formatter /json-formatter POST /api/json-formatter
Base64 Encoder / Decoder /base64 POST /api/base64
Image Converter /image-converter POST /api/image-converter
Image Resizer /image-resizer POST /api/image-resizer
Background Remover /background-remover POST /api/background-remover
Hash Generator /hash-generator POST /api/hash-generator
UUID Generator /uuid-generator POST /api/uuid-generator
URL Encoder / Decoder /url-encoder POST /api/url-encoder
Timestamp Converter /timestamp-converter POST /api/timestamp-converter
JSON to CSV /json-to-csv POST /api/json-to-csv
Text Case Converter /text-case-converter POST /api/text-case-converter
Color Converter /color-converter POST /api/color-converter
Number Base Converter /number-base-converter POST /api/number-base-converter
LCOV Viewer /lcov-viewer POST /api/lcov-viewer

Three interfaces, one domain

Human UI — browser-based, no sign-up, no upload to a server. Image tools use WebAssembly in your browser; text tools run client-side JS.

REST API — every tool is POST /api/<slug>, JSON in, JSON out. Free tier: 30 req/60s watermarked. OpenAPI 3.1 spec at /openapi.json.

MCP server — a single MCP endpoint covers all 15 tools. AI agents (Claude, Cursor, Continue, etc.) can discover and call any tool via the Model Context Protocol.

GET  https://quickhelp.dev/openapi.json    # OpenAPI 3.1 — all tools
GET  https://quickhelp.dev/llms.txt        # llms.txt discovery surface
GET  https://quickhelp.dev/llms-full.txt   # full per-tool docs for LLMs
POST https://quickhelp.dev/mcp             # MCP HTTP (JSON-RPC 2.0)

Use the MCP server

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "quickhelp": {
      "command": "npx",
      "args": ["-y", "quickhelp-mcp"]
    }
  }
}

Claude Code (CLI)

claude mcp add --transport http quickhelp https://quickhelp.dev/mcp

Hosted HTTP endpoint (any MCP client)

POST https://quickhelp.dev/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}

Quick API example

# Decode a JWT
curl -X POST https://quickhelp.dev/api/jwt-decoder \
  -H 'Content-Type: application/json' \
  -d '{"token":"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIn0.dozjgNryP4J3jVmNHl0w5N_XgL0n3I9PlFUP0THsR8U"}'

# Convert a colour
curl -X POST https://quickhelp.dev/api/color-converter \
  -H 'Content-Type: application/json' \
  -d '{"color":"#FF5733","from":"hex","to":"hsl"}'

# Generate UUIDs
curl -X POST https://quickhelp.dev/api/uuid-generator \
  -H 'Content-Type: application/json' \
  -d '{"version":"v4","count":5}'

Repo structure

quickhelp/
├── apps/web/          # Next.js 14 — human UI + REST API + discovery routes
├── apps/mcp/          # Standalone MCP stdio server (same registry)
├── packages/tool-kit/ # defineTool() contract + Zod helpers
├── packages/agent-sdk/# buildOpenAPI(), buildLlmsTxt(), buildMcpTools()
├── packages/ui/       # Shared UI components
├── packages/seo/      # MetaTags + JSON-LD
├── packages/tools/    # One package per tool
└── tooling/           # CLI scaffolder (pnpm create-tool <slug>)

Local development

pnpm install
pnpm dev          # web app at localhost:3000

Adding a new tool

pnpm create-tool <slug>
# Fill in packages/tools/<slug>/src/manifest.ts
# Tool auto-appears in UI, API, OpenAPI, llms.txt, and MCP — no extra wiring

Design principles

  • No auth, no database, no LLM calls — every tool is stateless and finishes in <5s.
  • Privacy-first — image processing runs in your browser via WebAssembly; nothing is uploaded.
  • Single-domain aggregation — one /openapi.json, one /mcp, one /llms.txt so agents resolve tool discovery in one request.
  • Free tier, always — anonymous use is free (watermarked output, 30 req/60s).

⭐ If this is useful, a GitHub star helps other developers find it.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured