
Kultur.dev
io.github.kultur-devPublished by GitHub account kultur-devv1.0.0Updated Oct 24, 2026
Cultural Intelligence Infrastructure for AI Agents — 200+ markets, 15 tones, 8 tools
Overview
Kultur.dev is a remote MCP server that gives an assistant cultural intelligence: it analyzes text, images and video for cultural risk and localization across…
- What you can do
- Analyze cultures and markets: deep cultural context, communication styles, business etiquette, holiday calendars
- Check and rewrite content: scan text for cultural sensitivity with severity scores and fix suggestions, and get localization guidance across 15 tones
- Compare countries: side-by-side cultural comparison and Hofstede six-dimension scores with business implications
- Assess geopolitical risk: adaptive scoring across 12 risk categories
- Multimodal and streaming analysis: image and video cultural compliance checks, plus real-time video frame analysis over WebSocket
- Generate branded PDF cultural audit reports
- When to use it
- Useful when content, campaigns, product imagery or AI-generated text will be published in multiple countries and you want cultural sensitivity checks, localization tone guidance or country comparisons before launch. Also relevant for research on Hofstede dimensions and geopolitical risk scoring.
- Requirements
- Remote SSE endpoint; no local install needed, though npm and pip packages are also mentioned. Requires a Kultur.dev account and an API key sent as a Bearer token in the Authorization header. Network access to kultur.dev. Paid plans for all 200+ markets and streaming endpoints.
Installation
In SourceWeft
- Open Kultur.dev in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via SSE. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.kultur-dev%2Fkultur-dev/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"kultur-dev": {
"type": "sse",
"url": "https://kultur.dev/api/mcp-sse/sse",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
Cultural Intelligence Infrastructure for AI Agents
The multimodal cultural intelligence layer every AI agent and global company needs.
Analyze text, images, and video across 200+ markets before you ship, post, or launch.
Website • Docs • OpenAPI Spec • Quick Start • Tools • Pricing
[npm] [PyPI] [License] [Smithery]
Why Kultur.dev?
Every AI agent operating globally is flying blind without cultural intelligence. A thumbs-up gesture that's offensive in the Middle East. A color palette that signals death in East Asia. A marketing slogan that's a slur in Brazil. These aren't edge cases. They're the daily reality of operating globally without cultural awareness.
Kultur.dev is the world's first multimodal cultural intelligence infrastructure. It gives AI agents and global enterprises the ability to analyze text, images, and video for cultural risks, sensitivity, and localization across 200+ markets, before content goes live.
What Makes It Different
Kultur.dev goes beyond text. It analyzes images for visual taboos (colors, symbols, gestures) and video content for cultural compliance across regions. It covers 200+ markets with deep, verified cultural intelligence, not surface-level summaries.
Localization comes with 15 tone styles (formal, humble, celebratory, diplomatic, marketing, medical, legal, and more). Reports are branded, boardroom-ready PDF documents, not raw JSON. Risk scoring is real-time with actionable recommendations before content ships.
The platform includes Hofstede cultural dimensions with business implications and cross-country comparison, plus geopolitical risk analysis with adaptive EWA scoring across 12 risk categories.
Overview
Kultur.dev provides cultural intelligence as an API, enabling AI agents, LLMs, and enterprise software to understand cultural context, avoid sensitivity violations, and communicate effectively across 200+ markets and 50+ languages.
The MCP (Model Context Protocol) server exposes 9 specialized tools plus multimodal and streaming endpoints that any MCP-compatible client can use:
MCP Tools
Multimodal & Streaming Endpoints
Report Generation
Quick Start
Option 1: SSE Transport (Recommended)
Connect any MCP client to the Kultur.dev SSE endpoint:
Authentication via Bearer token in the Authorization header.
Option 2: Claude Desktop
Add to your claude_desktop_config.json:
Option 3: Cursor IDE
Add to your Cursor MCP settings (.cursor/mcp.json):
Option 4: Windsurf IDE
Add to your Windsurf MCP configuration:
Option 5: VS Code / GitHub Copilot
Add to your VS Code settings.json:
Option 6: Cline
Add to your Cline MCP settings:
Option 7: npm
Option 8: pip
REST & Streaming API
For non-MCP integrations, Kultur.dev provides a comprehensive REST and WebSocket API:
Text Analysis
Multimodal & Streaming Analysis
Reports
Example: Real-time Streaming (WebSocket)
Authentication
All requests require a valid API key passed as a Bearer token:
Get Your API Key
- Visit kultur.dev
- Sign up for a plan
- Copy your API key from the dashboard
Pricing
Free tier includes full access to all tools including multimodal analysis. Pro and Enterprise tiers provide clean, production-ready responses and access to Real-time Streaming endpoints.
Use Cases
For Podcasters & Broadcasters: Real-time cultural monitoring of live video feeds to ensure global brand safety. Instant alerts for visual taboos or sensitive gestures during live streaming.
For AI Agents & LLMs: Cultural context injection before generating responses about specific countries. Real-time sensitivity checking on AI-generated content (text, images, and video). Localization guidance for multi-market content generation. Visual content screening before publishing to international audiences.
For Global Enterprises: CRM systems that adapt communication style per market. Marketing teams launching campaigns across culturally diverse regions. E-commerce platforms expanding internationally with culturally appropriate imagery. Compliance teams ensuring brand safety across all regions. HR platforms with cultural onboarding intelligence.
For Developers: Add cultural awareness to any application in minutes. Hofstede dimensions for academic and business research. Geopolitical risk scoring for supply chain and investment analysis. Multimodal content screening pipelines.
Who Needs Kultur.dev
Every AI agent operating across borders. Every global marketing team. Every e-commerce platform expanding internationally. Every content platform serving diverse audiences. Every localization team that needs more than translation. They need cultural adaptation. Every compliance team responsible for brand safety across regions.
The cost of a cultural mistake is measured in millions. The cost of preventing one is an API call.
Server Discovery
The MCP server card is available at:
OpenAPI specification:
Composio Toolkit
Kultur.dev is also available as a native Composio toolkit for LangChain, CrewAI, and OpenAI integrations:
The toolkit provides 8 LocalAction tools:
LangChain Example
Support
Documentation: kultur.dev/docs | Email: [email protected] | Issues: GitHub Issues
License
MIT License. See LICENSE for details.
Source: README.md at commit 5e5d7b2
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
60% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts