Dali by Lulu: MCP server, setup and security

What Dali by Lulu does

According to its repository: “Score AI image and video generation prompts for models like Veo 3, Sora, Kling, Midjourney and Flux, and rewrite weak ones before generating.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Dali by Lulu is listed under Image, video and audio, a category of 67 servers in the directory, where it ranks #54 by stars.

Topics declared by the repository: claude, generative-ai, prompt-engineering.

Installing and connecting Dali by Lulu

Distribution modes declared in the official MCP registry:

• PyPI package (Python, started with uvx or pip)
• remote server (streamable-http): you connect to it by URL, with nothing to install locally

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Dali by Lulu. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on July 7, 2026, the Lulu-The-Narwhal/dali-mcp repository has 9 stars and 0 forks, with 0 open issues. It has more stars than 24% of the servers in the directory. Last change 3 months ago. Version published in the registry: 0.6.1 (July 13, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.