luma-mcp
Verified Safeby JochenYang
Overview
Provides visual understanding capabilities to AI assistants that do not natively support image analysis, supporting multiple vision models.
Installation
npx luma-mcpEnvironment Variables
- MODEL_PROVIDER
- ZHIPU_API_KEY
- SILICONFLOW_API_KEY
- DASHSCOPE_API_KEY
- MODEL_NAME
- MAX_TOKENS
- TEMPERATURE
- TOP_P
- ENABLE_THINKING
Security Notes
The server correctly loads API keys from environment variables, avoiding hardcoding secrets. It uses standard `axios` for external API calls to well-known LLM providers. Local file access for images is handled by `fs/promises` and validated for size and format. Remote image URLs are passed directly to the vision models, meaning the server itself doesn't fetch arbitrary remote URLs, reducing a potential attack vector. The `sharp` library is used for image compression, which is a standard and generally safe practice. No 'eval' or obvious malicious patterns found.
Similar Servers
mcp-omnisearch
A Model Context Protocol (MCP) server that provides unified access to multiple search providers, AI tools, and content processing/enhancement features through a single interface.
tmcp
Build Model Context Protocol (MCP) servers for AI agents to interact with external tools and data sources, enabling LLMs to access context and perform actions.
mcp-servers
An MCP Server for robust web content fetching, anti-bot bypassing, intelligent caching, and LLM-powered information extraction from the open internet, designed for agent-building frameworks and MCP clients.
1xn-vmcp
An open-source tool for composing, customizing, and extending multiple Model Context Protocol (MCP) servers into a single logical, virtual MCP server, facilitating fine-grained context-engineering for AI workflows and agents.