3gpp
MCP server from edhijlu/3gpp-mcp-server
claude mcp add --transport stdio edhijlu-3gpp-mcp-server npx 3gpp-mcp-charging@latest serve \ --env HUGGINGFACE_TOKEN="optional-for-enhanced-access"
How to use
This MCP server provides direct access to 3GPP specifications via the TSpec-LLM dataset, enabling agent-ready responses with structured content. It exposes a set of MCP tools that let your AI agent search for specifications, fetch detailed metadata, compare multiple specifications, and extract implementation requirements. Tools include search_specifications for focused queries, get_specification_details for full specification metadata and guidance, compare_specifications for migrations and evolution analysis, and find_implementation_requirements for technical requirements and testing guidance. Configure your MCP client to route queries through the 3gpp-server so responses are drawn from real-time 3GPP data rather than generic training data, with optional HuggingFace token support for enhanced access. The setup emphasizes low latency, stateless operation, and agent-friendly JSON outputs suitable for automated workflows.
How to install
Prerequisites:
- Node.js 18+ installed on your system
- npm (comes with Node.js) or pnpm/yarn as preferred
- Internet connection for external API access
Option 1: Direct MCP Configuration (Recommended)
- No local installation needed. Use the MCP config below to run via npx within your MCP client.
Option 2: Development Setup
- Clone the repository (if you have the source): git clone <repository-url> cd 3gpp-mcp-server/3gpp-mcp-server-v2
- Install dependencies and build: npm install npm run build
- Start the server: npm run start
Option 3: Auto-Configuration
- Use the one-command auto-configuration: npx 3gpp-mcp-charging@latest init
Client configuration (example, omitted fields for brevity):
- Ensure your MCP client is configured to point to the above mcpServers entry.
- Use the provided command and arguments to launch the server, and supply any optional environment variables as needed.
Additional notes
Environment variables and configuration tips:
- HUGGINGFACE_TOKEN (optional): Enables enhanced access to TSpec-LLM resources; supply if available.
- CACHE_TIMEOUT (seconds): Control how long responses are cached. Example: export CACHE_TIMEOUT=3600
- ENABLE_CACHING: Enable or disable caching (true/false). Ensure appropriate caching strategy for your workload.
- If you encounter authentication or API access issues, verify network access to Hugging Face and 3GPP APIs, and ensure the MCP client passes the correct env vars.
- This server emphasizes a small (<10MB) stateless footprint with external API calls; ensure your hosting environment allows outbound API access.
Related MCP Servers
iterm
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
mcp
Octopus Deploy Official MCP Server
furi
CLI & API for MCP management
editor
MCP Server for Phaser Editor
DoorDash
MCP server from JordanDalton/DoorDash-MCP-Server
mcp
MCP сервер для автоматического создания и развертывания приложений в Timeweb Cloud