Back to MCP Servers
🔌

FrameThrower MCP

Find film stills, movie screenshots and cinematography references inside AI assistants for inspiration, learning and making movies faster. FrameThrower MCP provides search_frames, find_by_craft, find_similar and get_frame_details. Connect to the hosted server at https://framethrower.ai/api/mcp using OAuth 2.1. The install command below uses the documented mcp-remote bridge for stdio clients. $2 free credits on signup, then usage-based credits. Documentation: https://framethrower.ai/mcp — Product: https://framethrower.ai — Contact: leo@framethrower.ai

SearchAPI

Install

npx -y mcp-remote https://framethrower.ai/api/mcp

claude_desktop_config.json

claude_desktop_config.json
{
  "mcpServers": {
    "framethrower-mcp-zbo4": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://framethrower.ai/api/mcp"
      ]
    }
  }
}

Add this to your Claude Desktop config file. Find it at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.

What this does

FrameThrower MCP exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation. That makes it useful when you want Claude to reach into search engines and knowledge bases without copy-pasting context every turn.

Common use cases

  • •Search the open web, internal docs, or a vector store from inside a Claude session
  • •Bring fresh information past Claude's training cutoff into context
  • •Run multi-source research without copy-pasting URLs and snippets