NoLang

Provides a standardized interface to the NoLang AI-powered video service, enabling local and remote clients to generate and manage videos.
  • python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "team-tissis-nolang-mcp": {
      "command": "uvx",
      "args": [
        "nolang-mcp-stdio"
      ],
      "env": {
        "NOLANG_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

NoLang MCP Server provides a standardized interface to interact with the NoLang AI-powered video generation API. You can run the server locally to connect your MCP clients, such as Claude Desktop, to NoLang for real-time video creation via a simple, unified workflow.

How to use

You can use the NoLang MCP Server from a local client in STDIO mode or via HTTP if you expose it remotely. STDIO mode is designed for local clients like Claude Desktop, while HTTP mode enables remote access for multiple clients.

How to install

Prerequisites: You need Python 3.12 or newer. You also require a NoLang API key to authenticate requests.

Install a Python environment manager to isolate dependencies. The recommended approach is to use uv to manage environments and dependencies.

Install uv on macOS/Linux using the official installer or Homebrew. Run these commands in a terminal:

# Using the official installer
curl -LsSf https://astral.sh/uv/install.sh | sh

# Or using Homebrew
brew install uv

On Windows, install uv with PowerShell so you can run the MCP server locally.

# Using PowerShell
irm https://astral.sh/uv/install.ps1 | iex

Configuration and usage notes

Set your NoLang API key as an environment variable before starting the server.

Example (Unix-like shells):

export NOLANG_API_KEY=your_api_key_here

Starting the server in STDIO mode

The STDIO configuration is designed for local clients like Claude Desktop. Use the following startup configuration to run the STDIO MCP server.

# Start via UVX with the STDIO MCP
uvx nolang-mcp-stdio

# Or run directly via Python if you prefer
python -m nolang_mcp.runner.run_stdio

Starting the server in HTTP mode for remote access

If you want remote access for multiple clients, run the HTTP MCP server. The default port is 7310, and you can customize it with an environment variable.

# Start in HTTP mode (default port: 7310)
nolang-mcp-http

# Or
python -m nolang_mcp.runner.run_http

# Start with a custom port
NOLANG_MCP_PORT=8080 nolang-mcp-http

Exposing HTTP MCP server securely (optional)

If you want a quick, temporary remote URL without DNS or auth setup, you can use a Cloudflare Tunnel. Start the MCP server locally and then create a tunnel to expose it.

# 1) Install Cloudflare Tunnel CLI (macOS)
brew install cloudflared

# 2) Start the MCP server in another terminal (requires API key)
export NOLANG_API_KEY=your_api_key_here
# Optional: change port (default: 7310)
# export NOLANG_MCP_PORT=7310
nolang-mcp-http
# or
# python -m nolang_mcp.runner.run_http

# 3) Start a Quick Tunnel in a new terminal
cloudflared tunnel --url http://localhost:${NOLANG_MCP_PORT:-7310}
# You will get a URL like: https://xxxxx.trycloudflare.com

Notes on security and maintenance

Keep your NoLang API key secure. Do not share it in client configurations that could be exposed publicly. When exposing HTTP MCP server via tunnels, consider longer-term access controls or dedicated DNS and authentication when you move beyond temporary testing.

Available tools

generate_video_with_setting

Start video generation using a VideoSetting ID and optional prompts and media paths. Requires video_setting_id and at least one of the optional parameters like text, image_paths, pdf_path, pptx_path, audio_path, video_path.

generate_video_with_template

Start video generation using an official template Video ID and optional media inputs, mirroring the setting-based flow with a predefined template.

wait_video_generation_and_get_download_url

Poll the server for the status of a video generation job and return the final download URL when complete.

list_generated_videos

Retrieve a paginated list of videos you have generated.

list_video_settings

Retrieve a paginated list of your VideoSettings.

recommend_templates

Suggest official templates based on the video mode and optional query to guide your creation.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
NoLang MCP Server - team-tissis/nolang-mcp | VeilStrat