We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PyJudge/pdf4vllm-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
config.example.json•1.16 kB
{
"_comment": "PDF MCP for vLLM Configuration - Copy this to config.json and modify as needed",
"max_pages_per_request": 10,
"_max_pages_per_request_comment": "Maximum pages per read request (default: 10). Increase for longer documents, decrease to limit context size.",
"max_images_per_request": 50,
"_max_images_per_request_comment": "Maximum images per read request (default: 50). Adjust based on your LLM's context window.",
"max_image_dimension": 842,
"_max_image_dimension_comment": "Maximum image dimension in pixels (default: 842 = A4 height at 100 DPI). Images larger than this are scaled down.",
"min_image_dimension": 28,
"_min_image_dimension_comment": "Minimum image dimension in pixels (default: 28). Images smaller than this are filtered out (removes separators, icons).",
"max_aspect_ratio": 15,
"_max_aspect_ratio_comment": "Maximum width/height ratio (default: 15). Filters extreme aspect ratios like lines and separators. Set to 0 to disable.",
"page_image_dpi": 100,
"_page_image_dpi_comment": "DPI for full page images when text is corrupted (default: 100). Higher values = larger images but better quality."
}