FrameThrower Film References — style skill for style references

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Film stills from 5,489 films, searchable by lighting, lens, shot size, color and mood.

• Type: Style · Style references
• Slug: framethrower
• Status: live
• Publisher: FrameThrower (vendor)
• License: MIT
• Source: https://github.com/framethrower-ai/framethrower-mcp
• Works in: Claude.ai, Claude Code, Cursor, Any MCP client
• Requires: FrameThrower account (OAuth; $2 free credit)
• Cost: Pay per use after the free credit
• Adoption: 1 GitHub stars (GitHub, 2026-10-26)

What it does

A remote MCP server over a cinematography library indexed frame by frame. Four tools: search frames by description, find by craft attribute (lighting, lens character, shot size, color, mood), find similar frames, and get frame details with film, director and DP credits. The fastest way for an agent to back a shot spec with real references.

Use when

• Show me real examples of this lighting
• Find frames similar to my reference
• Build a reference board for a scene

Not for

• Feeding film stills to an image or video model

Install

• Claude.ai: Settings → Connectors → Add custom connector → https://framethrower.ai/api/mcp
• Any MCP client: https://framethrower.ai/api/mcp

More style references skills

• Are.na MCP: Build and read Are.na moodboard channels from your agent.
• GPT Image 2 Style Library: Pick styles and industrial prompt templates for GPT Image 2/2.5 from a 530+ case library (a 35K-star repo).