3GPP FTP Remote MCP Server

A read-only remote MCP server for browsing public files from the 3GPP FTP service. It runs on Cloudflare Workers using TypeScript, Wrangler, and Streamable HTTP transport.

The MCP endpoint is /mcp. The server is stateless and does not require 3GPP credentials.

Tools

search(query: string)

Searches configured public 3GPP FTP roots by filename and path. Each result contains:

• id: canonical 3GPP FTP path used by fetch
• title: filename
• url: public 3GPP URL
• metadata: path, modified date, size, and extension when available

A direct path or 3GPP URL can also be passed as the query.

fetch(id: string)

Fetches one result by its canonical path. Text and HTML content is returned as text, up to the configured character limit. Binary formats such as ZIP, DOCX, and PDF currently return metadata and their public download URL; they are not saved by the Worker.

Project Layout

src/index.ts       Remote MCP server and tool registration
src/threegpp.ts    Public 3GPP listing, search, and fetch logic
src/types.ts       Worker environment and result types
wrangler.jsonc     Cloudflare Worker configuration
chatgpt-plugin/    ChatGPT registration metadata and setup guide
legacy-python/     Original Python MCP prototype

Prerequisites

• Node.js and npm
• A Cloudflare account for deployment

Verify the local tools:

node --version
npm --version

Install

cd /Users/kaum11699/Documents/2026/3gpp-ftp-connector
npm install
npm run typecheck

Run Locally

Start the Worker development server:

npm run dev

Wrangler normally serves it at http://localhost:8787. Confirm the Worker is running:

curl http://localhost:8787/

The response should advertise /mcp, Streamable HTTP, and the search and fetch tools.

Test with MCP Inspector

Keep npm run dev running and open a second terminal:

npx @modelcontextprotocol/inspector@latest

In Inspector:

1. Select Streamable HTTP.
2. Enter http://localhost:8787/mcp.
3. Connect and list the available tools.
4. Call search with a filename, path, or URL.
5. Pass a returned id to fetch.

Example search input:

{
  "query": "/ftp/tsg_sa/WG2_Arch/TSGS2_174_Malta_2026-04/Docs/S2-2601720.zip"
}

Example fetch input:

{
  "id": "/ftp/tsg_sa/WG2_Arch/TSGS2_174_Malta_2026-04/Docs/S2-2601720.zip"
}

Deploy

Authenticate Wrangler and deploy:

npx wrangler login
npm run deploy

With the default Worker name, the deployed endpoint is:

https://threegpp-ftp-mcp.<cloudflare-subdomain>.workers.dev/mcp

Wrangler prints the exact URL after a successful deployment.

Connect to ChatGPT

The maintained ChatGPT app/plugin name, description, registration values, and test prompts are in chatgpt-plugin/. Update that metadata when the public endpoint or tool behavior changes.

Configuration

Public configuration is stored in wrangler.jsonc:

• THREEGPP_BASE_URL: 3GPP website origin
• THREEGPP_FTP_ROOT: allowed FTP path root
• THREEGPP_SEARCH_ROOTS: comma-separated directories searched by default
• THREEGPP_SEARCH_MAX_DIRECTORIES: maximum directories visited per search
• THREEGPP_SEARCH_MAX_RESULTS: maximum results returned per search
• THREEGPP_FETCH_TEXT_LIMIT: maximum text characters returned by fetch

The Worker uses nodejs_compat because the Cloudflare Agents SDK currently includes dependencies that import Node built-in modules.

Current Scope

• Public 3GPP FTP access only
• Read-only MCP tools
• No portal authentication
• No persistent file downloads or storage
• No ZIP, Office, or PDF extraction inside the Worker

Heavy parsing can be added later through an external parser service or Cloudflare storage without changing the search and fetch tool contracts.

Legacy Python Prototype

The original Python/stdin implementation is retained under legacy-python/. It is not used by the Cloudflare Worker or required for deployment.