← Registry

AI & Machine Learning

happlen.com

Helps users create and refine prompts for AI models.

1 endpoint3 known toolsFirst detected July 25, 2026Last detected August 29, 2026

ENDPOINT 1

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

No auth detected

MCP server metadata

Name
rtcf
Version
1.0.0
Capabilities
tools.listChangedprompts.listChanged

Known tools 3

improve_prompt

Rewrite a rough prompt into a sharper, ready-to-use prompt structured as Role, Task, Context, Format (RTCF).

Inferred read-only
improve_followup

Write the user's NEXT message for an AI conversation that is already in progress (a follow-up).

Potential side effects
build_prompt

Compose a ready-to-use prompt from explicit Role, Task, Context, and Format parts.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.rtcf]
url = "https://rtcf.happlen.com/api/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "rtcf": {
      "type": "http",
      "url": "https://rtcf.happlen.com/api/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: rtcf
Remote MCP URL: https://rtcf.happlen.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "rtcf": {
      "url": "https://rtcf.happlen.com/api/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "rtcf": {
      "type": "http",
      "url": "https://rtcf.happlen.com/api/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "rtcf",
  "transport": "streamable-http",
  "url": "https://rtcf.happlen.com/api/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.