RTCF MCP

RTCF is a prompt improvement tool that restructures rough requests into sharp Role/Task/Context/Format prompts. The MCP server exposes tools like improve_prompt to rewrite requests and build_prompt to weave existing parts into one prompt, supporting Thai and English inputs.

Visit Happlen

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Happlen

MCP endpoint (Streamable HTTP)

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

Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

3 of 3 have a description · 0 of 3 declare behavior hints · 3 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 1:04 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Rewrite rough requests into structured prompts
Weave existing R/T/C/F parts into one prompt
Integrate with Claude and ChatGPT via custom connectors

Source and maintenance

Community listingRegistry 1.0.0

mcp-registry: io.github.hengkp/rtcf@1.0.0 Source repository Project website

Maintenance checked: Nov 7, 2026, 12:20 AM UTC

Protocol and capabilities

Server: rtcf 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 3 advertised
Resources: 1 advertised
Resource templates: 0 advertised
Prompts: 2 advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  },
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "listChanged": true
  }
}

Tools

3 advertised

improve_prompt

Advertised by the server during the last successful anonymous check.

Rewrite a rough prompt into a sharper, ready-to-use prompt structured as Role, Task, Context, Format (RTCF). Returns the improved prompt, its four parts, a short list of clarifying questions worth asking the user, and which model tier and effort level suit this kind of work. Use this before answering when the user's request is vague, or when the user asks to improve a prompt.

improve_prompt input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "maxLength": 8000,
      "minLength": 1,
      "description": "The rough prompt or request to restructure"
    },
    "target": {
      "enum": [
        "generic",
        "claude",
        "gpt"
      ],
      "type": "string",
      "description": "Which AI family will actually run the improved prompt (\"claude\" or \"gpt\"). Pass your own family so the wording is shaped for it and the model recommendation is concrete. Omit for a provider-neutral prompt."
    }
  },
  "additionalProperties": false
}

improve_followup

Advertised by the server during the last successful anonymous check.

Write the user's NEXT message for an AI conversation that is already in progress (a follow-up). Use when the user wants to refine, deepen, or continue earlier work in this conversation. Do NOT use it for a brand-new task (use improve_prompt for that). Returns a short, ready-to-send continuation message that anchors to the existing work instead of restarting it. Requires an API key (add ?key=rk_live_... to the connector URL).

improve_followup input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "next_request"
  ],
  "properties": {
    "next_request": {
      "type": "string",
      "maxLength": 8000,
      "minLength": 1,
      "description": "What the user wants next, or where they are stuck, in their own words"
    },
    "original_goal": {
      "type": "string",
      "maxLength": 8000,
      "description": "The original goal or starter prompt of the conversation, if known"
    },
    "conversation_summary": {
      "type": "string",
      "maxLength": 20000,
      "description": "2-6 sentences summarizing what the AI last produced and any key decisions so far (you can see the conversation; the tool cannot)"
    }
  },
  "additionalProperties": false
}

build_prompt

Advertised by the server during the last successful anonymous check.

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.

build_prompt input schema

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

Prompts

2 advertised

rtcf-next

Advertised by the server during the last successful anonymous check.

Continue an ongoing conversation well: turn your rough next ask into a sharp follow-up message (no RTCF restart).

request: What you want next, roughly, in any language (required)

rtcf

Advertised by the server during the last successful anonymous check.

Improve a rough prompt with RTCF (Role, Task, Context, Format), then answer it. Paste your rough request.

prompt: Your rough prompt or request, in any language (required)

Resources

1 advertised

RTCF result card

Advertised by the server during the last successful anonymous check.

Result card for improve_prompt, improve_followup and build_prompt

RTCF result card URI

ui://rtcf/card-v1.html

MIME type: text/html;profile=mcp-app

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 976 ms
95th percentile latency: 976 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 1:04 AM UTC · probe · passed · 976 ms · metadata changed · 3 tool(s), 1 resource(s), 0 resource template(s), 2 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add rtcf-mcp --url https://rtcf.happlen.com/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable rtcf-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "rtcf-mcp": {
      "url": "https://rtcf.happlen.com/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "rtcf-mcp": {
      "type": "streamableHttp",
      "url": "https://rtcf.happlen.com/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start rtcf-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "rtcf-mcp": {
      "type": "http",
      "url": "https://rtcf.happlen.com/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

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

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

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

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "rtcf-mcp": {
      "serverUrl": "https://rtcf.happlen.com/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like RTCF MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 5,453

RTCF MCP

Endpoint and access

What its tools do

Not annotated (3)

Checks and signals

What you can do with it

Source and maintenance

Protocol and capabilities

Tools

Prompts

Resources

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other productivity and knowledge servers