Skip to main content
Glama

PDF Knowledgebase MCP Server

by juanqui
.env.dev1.51 kB
# Development environment variables for pdfkb-mcp Docker container # Copy this file to .env.dev and customize for your development environment # === Core Configuration === PDFKB_DOCUMENTS_PATH=./documents PDFKB_CACHE_PATH=./dev-cache PDFKB_LOGS_PATH=./dev-logs PDFKB_LOG_LEVEL=DEBUG # === Transport Configuration === PDFKB_TRANSPORT=http PDFKB_MCP_PORT=8001 # === Embedding Configuration === # Default: local embeddings (no API key required) PDFKB_EMBEDDING_PROVIDER=local PDFKB_LOCAL_EMBEDDING_MODEL=Qwen/Qwen3-Embedding-0.6B # Uncomment and set if using OpenAI embeddings # PDFKB_EMBEDDING_PROVIDER=openai # PDFKB_OPENAI_API_KEY=sk-proj-your-key-here # PDFKB_EMBEDDING_MODEL=text-embedding-3-large # Uncomment and set if using HuggingFace embeddings # PDFKB_EMBEDDING_PROVIDER=huggingface # HF_TOKEN=hf_your_token_here # PDFKB_HUGGINGFACE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2 # === Web Interface Configuration === PDFKB_WEB_ENABLE=true PDFKB_WEB_PORT=8000 # === Processing Configuration === PDFKB_PDF_PARSER=pymupdf4llm PDFKB_DOCUMENT_CHUNKER=langchain PDFKB_CHUNK_SIZE=500 # Smaller chunks for faster development PDFKB_CHUNK_OVERLAP=50 # Smaller overlap for faster development # === Search Configuration === PDFKB_ENABLE_HYBRID_SEARCH=true PDFKB_ENABLE_RERANKER=false PDFKB_ENABLE_SUMMARIZER=false # === Performance Configuration === # Conservative settings for development PDFKB_MAX_PARALLEL_PARSING=1 PDFKB_MAX_PARALLEL_EMBEDDING=1 PDFKB_BACKGROUND_QUEUE_WORKERS=1

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/juanqui/pdfkb-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server