Skip to main content
Glama

PocketMCP

.env.sample4.47 kB
# PocketMCP Environment Configuration # Copy this file to .env and customize the values for your environment # ============================================================================= # DATABASE CONFIGURATION # ============================================================================= # Path to the SQLite database file # Default: ./data/index.db SQLITE_PATH=./data/index.db # ============================================================================= # EMBEDDING MODEL CONFIGURATION # ============================================================================= # Hugging Face model ID for text embeddings # Default: Xenova/all-MiniLM-L6-v2 # Other options: sentence-transformers/all-MiniLM-L6-v2, sentence-transformers/all-mpnet-base-v2 MODEL_ID=Xenova/all-MiniLM-L6-v2 # ============================================================================= # TEXT CHUNKING CONFIGURATION # ============================================================================= # Size of text chunks for processing (in characters) # Default: 1000 # Recommended range: 500-2000 CHUNK_SIZE=1000 # Overlap between consecutive chunks (in characters) # Default: 120 # Recommended: 10-20% of CHUNK_SIZE CHUNK_OVERLAP=120 # ============================================================================= # FILE WATCHING CONFIGURATION # ============================================================================= # Directory to watch for file changes (optional) # If not set, file watching is disabled # Example: ./documents or /path/to/your/documents WATCH_DIR= # ============================================================================= # DEVELOPMENT CONFIGURATION # ============================================================================= # Node environment # Options: development, production, test NODE_ENV=development # Enable debug logging for dotenv # Options: true, false DEBUG_DOTENV=false # ============================================================================= # ADVANCED CONFIGURATION # ============================================================================= # Maximum number of concurrent file processing operations # Default: 5 MAX_CONCURRENT_FILES=5 # Enable verbose logging # Options: true, false VERBOSE_LOGGING=false # Custom data directory (overrides SQLITE_PATH directory) # DATA_DIR=./custom-data # ============================================================================= # HUGGING FACE CONFIGURATION (Optional) # ============================================================================= # Hugging Face API token (for private models or increased rate limits) # HF_TOKEN=your_hugging_face_token_here # Cache directory for downloaded models # HF_CACHE_DIR=./cache/huggingface # ============================================================================= # PDF PROCESSING CONFIGURATION # ============================================================================= # Maximum number of pages to process in a PDF file # Default: 300 # PDFs with more pages will be marked as 'too_large' and skipped PDF_MAX_PAGES=300 # Minimum number of text characters required in a PDF # Default: 500 # PDFs with less text will be marked as 'needs_ocr' and skipped PDF_MIN_TEXT_CHARS=500 # ============================================================================= # DOCX PROCESSING CONFIGURATION # ============================================================================= # Maximum file size in bytes for DOCX files # Default: 10000000 (10MB) # DOCX files larger than this will be marked as 'too_large' and skipped DOC_MAX_BYTES=10000000 # Whether to split DOCX documents on headings (h1/h2) # Default: false # If true, creates separate segments for each heading section DOCX_SPLIT_ON_HEADINGS=false # ============================================================================= # MCP SERVER CONFIGURATION # ============================================================================= # MCP transport mode # Options: stdio, http, both TRANSPORT=both # HTTP server configuration (when using http transport) HTTP_HOST=0.0.0.0 HTTP_PORT=8001 # Log level for MCP server # Options: debug, info, warn, error LOG_LEVEL=info # ============================================================================= # WEB INTERFACE CONFIGURATION # ============================================================================= # API server port for web interface API_PORT=5174 # API server bind address API_BIND=127.0.0.1

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/Kailash-Sankar/PocketMCP'

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