🧑‍💻

Free Developer Tools — Format, Encode, Decode & Convert

A focused toolbox for everyday development work: format and validate JSON, encode and decode Base64 and URLs, decode and verify JWTs, test regular expressions, generate hashes and UUIDs, convert timestamps, and calculate subnets — plus a full set of MCP and AI-agent tools for building and securing Model Context Protocol servers.

Every tool here runs entirely in your browser. That's not just a speed benefit — it means API responses, tokens, secrets, MCP configs and customer data you paste in are never transmitted anywhere. No signup, no rate limits, no waiting on a server round-trip.

{ } JSON11

64 Base644

🔗 URL4

🤖 MCP & Agents18

🛡

MCP Security Scanner

Scan an MCP server config for prompt-injection, exfiltration & tool poisoning.

🔌

MCP Config Generator

Generate a valid MCP server config for Claude, Cursor, VS Code & Windsurf.

🧪

MCP Config Validator

Validate an mcp.json / claude_desktop_config.json and catch common mistakes.

🕵

Prompt Secret Redactor

Mask API keys, tokens & PII in a prompt before you send it to an LLM.

🛑

Prompt Injection Checker

Scan untrusted text for prompt-injection patterns before feeding it to an agent.

🧰

Tool Definition Generator

Generate a tool/function-calling schema for MCP, Anthropic (Claude) & OpenAI.

🔬

MCP tools/list Inspector

Inspect & validate an MCP tools/list response — params, required fields & schema issues.

📐

System Prompt Linter

Review a system prompt for role clarity, guardrails & prompt-injection resistance.

🔀

Tool Definition Converter

Convert a tool/function schema between MCP, Anthropic (Claude) & OpenAI formats.

🧬

MCP Config Merger

Merge multiple MCP server configs into one file — deduped, with conflicts flagged.

🗒

Prompt Template Manager

Fill {{variables}} in a reusable prompt with a live preview and missing-value checks.

🕸

WebMCP Tool Generator

Generate WebMCP tool definitions — declarative HTML & imperative JS — to make your site agent-ready.

📡

WebMCP Readiness Checker

Check your page HTML for WebMCP tools and get agent-readiness fixes — is your site WebMCP-ready?

🧠

Deep Agent Scaffold Generator

Design a deep agent (planning, subagents, tools) → get runnable LangChain deepagents code + a diagram.

🎯

LLM Red-Team Prompt Generator

Generate adversarial test prompts to red-team your own AI agent — mapped to the OWASP LLM Top 10.

🛡

OWASP LLM Top 10 Assessment

Self-assess your LLM app against the OWASP LLM Top 10 — get a risk score and mitigations.

🔧

JSON Schema to Zod / Pydantic / TypeScript

Convert a JSON Schema to Zod, a Pydantic model or a TypeScript interface for typed LLM tools & APIs.

📊

Context Window / Token Budget Planner

Plan a prompt's token budget against a model's context window — system, RAG, history, output & cost.

🔑 JWT3

More Developer tools

What's included

  • JSON — formatter and validator, tree viewer, diff, repair, schema generator, JSONPath tester, and converters to TypeScript, CSV, YAML and XML.
  • JWT — decoder, encoder/signer and signature verifier using the Web Crypto API.
  • Base64 — text, file, image and data-URI encoding and decoding.
  • URL — percent encoder/decoder, URL parser, query-string builder and slug generator.
  • Utilities — regex tester, hash generator, UUID generator, timestamp converter, case converter and CIDR calculator.
  • MCP & Agents — MCP config generator and validator, security scanner, tools/list inspector, tool-definition (schema) generator, system-prompt linter, secret redactor and injection checker for people building with AI agents.

Why local processing matters for developers

Debugging usually means pasting real data — a production API response, an auth token, a config file. Pasting those into a tool that posts them to someone else's server is a quiet security problem, and one that's easy to overlook under time pressure. Because these tools compute in the browser, the data stays in the tab you're working in. You can use them on internal payloads without a second thought, and they keep working offline once the page has loaded.

Frequently asked questions

Is my data sent to a server?

No. Every developer tool here runs in your browser using JavaScript and the Web Crypto API, so what you paste never leaves your machine.

Can I use these on production data?

That's exactly the point of processing locally — nothing is transmitted or logged. As a general habit, still avoid pasting live production secrets into any web page, ours included.

Do the tools work offline?

Once a tool page has loaded, the processing itself needs no network connection, so it keeps working if you go offline.

Is there any rate limit or signup?

Neither. There's no account, no quota and no throttling, because there's no server doing the work.