Rtcf

Official2 tools

by hengkp

Turns rough requests into sharp Role/Task/Context/Format prompts. Thai and English.

Topics

chatgptclaudemcpmcp-serverprompt-engineeringthai

Captured live from the server via tools/list.

improve_prompt

Rewrite a rough prompt into a sharper, ready-to-use prompt structured as Role, Task, Context, Format (RTCF). Returns the improved prompt plus its four parts. Use this before answering when the user's request is vague, or when the user asks to improve a prompt.

Parameters1

prompt

string

required

The rough prompt or request to restructure

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 8000,
      "description": "The rough prompt or request to restructure"
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

build_prompt

Compose a ready-to-use prompt from explicit Role, Task, Context, and Format parts. Use when the user already knows the pieces and wants them woven into one clean prompt.

Parameters4

role	string	required	Who the AI should be
task	string	required	What the AI should do
context	string	optional	Background the AI needs
format	string	optional	How the answer should be shaped

Raw schema

{
  "type": "object",
  "properties": {
    "role": {
      "type": "string",
      "maxLength": 2000,
      "description": "Who the AI should be"
    },
    "task": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "What the AI should do"
    },
    "context": {
      "type": "string",
      "maxLength": 4000,
      "description": "Background the AI needs"
    },
    "format": {
      "type": "string",
      "maxLength": 2000,
      "description": "How the answer should be shaped"
    }
  },
  "required": [
    "role",
    "task"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md2 KBView on GitHub

RTCF — Prompt Improver (Remote MCP Server)

Turn rough requests into sharp, structured prompts, right inside Claude, ChatGPT, or any MCP client.

RTCF rewrites a messy request into the four parts every strong prompt needs: Role, Task, Context, Format. Works in Thai and English. Free tier included (5 credits/day, no sign-up).

Website: https://rtcf.happlen.com
Setup guide: https://rtcf.happlen.com/docs
By Happlen

Endpoint

This is a hosted (remote) MCP server. No installation, no OAuth setup:

code

https://rtcf.happlen.com/api/mcp

Transport: Streamable HTTP. On a paid plan, append your key: https://rtcf.happlen.com/api/mcp?key=rk_live_...

Tools

Tool	What it does	Cost
`improve_prompt`	Rewrites a rough request into the RTCF structure and returns a ready-to-use improved prompt	1+ credit
`build_prompt`	Weaves existing Role/Task/Context/Format parts into one clean prompt	Free

Quick setup

Claude (web / desktop / mobile)

Settings -> Connectors -> Add custom connector
Paste https://rtcf.happlen.com/api/mcp (leave OAuth fields empty)
In a chat, enable the connector and say: "Improve this prompt with RTCF, then answer it."

ChatGPT (paid plans, Developer mode)

Settings -> Apps -> Advanced -> enable Developer mode
Add a custom connector with the same URL
Ask ChatGPT to use RTCF

Claude Code

bash

claude mcp add --transport http rtcf https://rtcf.happlen.com/api/mcp

REST API

bash

curl -X POST https://rtcf.happlen.com/api/v1/convert \
  -H "Authorization: Bearer rk_live_..." \
  -H "Content-Type: application/json" \
  -d '{"prompt": "help me write an email to my professor"}'

Full API docs: https://rtcf.happlen.com/docs

ภาษาไทย

RTCF คือผู้ช่วยปรับพรอมต์สำหรับคนที่ใช้ AI แล้วไม่รู้จะพิมพ์อะไรดี วางคำขอคร่าว ๆ แล้วรับพรอมต์โครงสร้าง Role, Task, Context, Format กลับไปใช้ได้ทันที ใช้ฟรีวันละ 5 เครดิต ไม่ต้องสมัครสมาชิก ใช้ได้ทั้งบนเว็บ ใน Claude และ ChatGPT ผ่านลิงก์ MCP ด้านบน

Questions: hello@happlen.com

Install

Tools (2)

improve_promptbuild_prompt

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://rtcf.happlen.com/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "rtcf": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://rtcf.happlen.com/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.