NoLang MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@NoLang MCP Server create a video about sustainable energy using my slideshow template"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
NoLang MCP Server
Enable any MCP Client like Claude Desktop or Agents to use the NoLang API to generate AI-powered videos
What is NoLang?
NoLang is an AI-powered video generation service developed by Mavericks that creates videos in real-time. This MCP server provides a standardized interface to interact with the NoLang API.
Related MCP server: ShotFlow MCP Server
Prerequisites
Python 3.12+
NoLang API key (Get it from the NoLang dashboard: NoLang API > API Key)
Installation
We recommend using uv to manage Python environments and dependencies.
Install uv
macOS/Linux
# Using the official installer
curl -LsSf https://astral.sh/uv/install.sh | sh
# Or using Homebrew
brew install uvWindows
# Using PowerShell
irm https://astral.sh/uv/install.ps1 | iexConfiguration
Set your NoLang API key to the environment variable:
export NOLANG_API_KEY=your_api_key_hereUsage
STDIO Mode (Claude Desktop etc.)
STDIO mode is designed for local clients such as Claude Desktop.
Claude Desktop Configuration
Add the following to your Claude Desktop configuration file:
macOS
~/Library/Application Support/Claude/claude_desktop_config.json
Windows
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"nolang": {
"command": "uvx",
"args": ["nolang-mcp-stdio"],
"env": {
"NOLANG_API_KEY": "your_api_key_here"
}
}
}
}Direct Execution
# Start in STDIO mode
nolang-mcp-stdio
# or
python -m nolang_mcp.runner.run_stdioHTTP Mode (Remote Access & Multiple Clients)
HTTP mode supports remote access via web and concurrent connections from multiple clients.
# Start in HTTP mode (default port: 7310)
nolang-mcp-http
# or
python -m nolang_mcp.runner.run_http
# Start with custom port
NOLANG_MCP_PORT=8080 nolang-mcp-httpHTTP mode: expose as remote MCP server (Cloudflare Tunnel / no DNS or auth)
Expose your local MCP HTTP server instantly using Cloudflare Tunnel Quick Tunnel. This generates a temporary trycloudflare.com URL with no DNS or authentication setup required.
# 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.comThe issued URL is random and temporary. For longer-term or access-controlled setups, consider a Named Tunnel or Cloudflare Access.
Available MCP Tools
generate_video_with_setting
Consumes paid credits. Start video generation using your VideoSetting ID.
Required Parameters:
video_setting_id(string): UUID of VideoSetting (obtainable vialist_video_settings)
Optional Parameters (at least one is required):
text(string): Text prompt (for QUERY modes or slideshow_analysis mode)pdf_path(string): Absolute path to PDF file (for slideshow_* modes)pptx_path(string): Absolute path to PPTX file (for slideshow_* modes)audio_path(string): Absolute path to audio file (for audio_speech mode, MP3/WAV/M4A/AAC)video_path(string): Absolute path to video file (for audio_video mode, MP4)image_paths(string): Image file paths (comma-separated, for QUERY modes)
generate_video_with_template
Consumes paid credits. Start video generation using an official template Video ID.
Required Parameters:
video_id(string): ID of generated or generating video
Optional Parameters:
Same parameters as
generate_video_with_settingare available
wait_video_generation_and_get_download_url
Polls until video generation completes and returns the download URL.
Parameters:
video_id(string, required): Video ID of the generation jobmax_wait_time(integer, optional): Maximum wait time in seconds (default: 600)check_interval(integer, optional): Status check interval in seconds (default: 10)
list_generated_videos
Return a paginated list of videos you have generated.
Parameters:
page(integer, optional): Page number (default: 1)
list_video_settings
Return a paginated list of your VideoSettings.
Parameters:
page(integer, optional): Page number (default: 1)
recommend_templates
Recommend official templates based on video mode and optional query.
Project Structure
nolang_mcp/server.py: Common MCP server definition and API clientnolang_mcp/runner/run_stdio.py: Entry point for STDIOnolang_mcp/runner/run_http.py: Entry point for HTTP
License
MIT License
Available Tools
6 toolsgenerate_video_with_settingC
Consumes paid credits. Start video generation using your VideoSetting ID. Provide text, pdf_path, pptx_path, audio_path, video_path, or image_paths as required.
Inputs: args (required). Returns: video_id
generate_video_with_templateC
Consumes paid credits. Start video generation using an official template Video ID. Provide text, pdf_path, pptx_path, audio_path, video_path, or image_paths as required.
Inputs: args (required). Returns: video_id
list_generated_videosB
Return a paginated list of videos you have generated.
Inputs: args (required). Returns: page, videos, has_next, total_videos
list_video_settingsC
Return a paginated list of your VideoSettings.
Inputs: args (required). Returns: page, has_next, settings, total_settings
recommend_templatesB
Recommend official templates based on video mode and optional query.
Inputs: args (required). Returns: templates
wait_video_generation_and_get_download_urlB
Polls until video generation completes and returns the download URL.
Inputs: args (required). Returns: status, video_id, download_url
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
The tools have clear distinctions in purpose, but there is some overlap between 'generate_video_with_setting' and 'generate_video_with_template' as both handle video generation with similar parameters, which could cause confusion. The other tools (list_generated_videos, list_video_settings, recommend_templates, wait_video_generation_and_get_download_url) are distinct and well-defined.
All tool names follow a consistent snake_case pattern with clear verb_noun structures (e.g., generate_video_with_setting, list_generated_videos). The naming is predictable and readable throughout the set, with no deviations in style.
With 6 tools, the count is well-scoped for a video generation server, covering key operations like generation, listing, and monitoring. Each tool appears to earn its place without being overly sparse or bloated.
The tool set covers core video generation workflows, including creation (with settings/templates), listing, and status monitoring. A minor gap exists in lacking explicit update or delete operations for videos or settings, but agents can likely work around this for basic usage.
Maintenance
Related MCP Connectors
Build, run, schedule, and publish AI video pipelines to YouTube and TikTok from any MCP client.
Direct AI video, image, music and storyboard production from any MCP client.
Generate AI video from any MCP client. Pick the model, see the per-second price before you spend.
AI video, image and audio generation with 140+ AI models from any MCP agent
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceEnables video generation from text, images, and more through MCP-compatible apps like Claude and Cursor.55MIT- AlicenseNot gradedqualityDmaintenanceEnables AI agents to generate professional storyboards and videos from scripts or creative descriptions via MCP-compatible clients.37 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables AI clients like Claude and ChatGPT to generate images and videos, animate images, create lip-synced videos, list TTS voices, and manage media via remote MCP tools.-
- AlicenseNot gradedqualityDmaintenanceExposes video generation and editing tools to MCP-capable clients, enabling text-to-video, image-to-video, video editing, reusable voice and character profiles, and task status queries through natural language.4MIT