# MCP Server Configuration
# MCP ReadPDFX Server v1.0.0 - Production Configuration
mcp:
version: "2025-06-18"
name: "mcp-readpdfx"
description: "MCP server for OCR PDF processing with comprehensive text extraction and analysis"
server:
name: "MCP ReadPDFX Server"
version: "1.0.0"
host: "localhost"
port: 8000
debug: false
# Server capabilities
capabilities:
tools:
listChanged: true
resources:
subscribe: false
listChanged: false
prompts:
listChanged: false
logging:
level: "info"
# Transport configuration
transport:
type: "http"
protocol: "json-rpc"
version: "2.0"
endpoints:
initialize: "/mcp/initialize"
tools:
list: "/mcp/tools/list"
call: "/mcp/tools/call"
jsonrpc: "/jsonrpc"
manifest: "/mcp/manifest"
health: "/health"
# OCR Configuration
ocr:
engine: "tesseract"
default_language: "eng+ind"
default_dpi: 300
max_workers: 4
timeout: 300
supported_languages:
- "eng" # English
- "ind" # Indonesian
- "eng+ind" # English + Indonesian
- "fra" # French
- "deu" # German
- "spa" # Spanish
- "ita" # Italian
- "por" # Portuguese
- "rus" # Russian
- "chi_sim" # Chinese Simplified
- "chi_tra" # Chinese Traditional
- "jpn" # Japanese
- "kor" # Korean
- "ara" # Arabic
- "hin" # Hindi
# PDF Processing Configuration
pdf:
max_file_size: "100MB"
supported_formats:
- "pdf"
text_density_threshold: 50 # Percentage threshold for OCR recommendation
preserve_layout: true
processing_modes:
- "smart" # Auto-detect best method
- "extract_only" # Digital text extraction only
- "ocr_only" # OCR processing only
# Batch Processing Configuration
batch:
max_files: 100
default_pattern: "*.pdf"
concurrent_jobs: 4
output_format: "txt"
# Logging Configuration
logging:
level: "INFO"
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
handlers:
- "console"
- "file"
file:
path: "logs/mcp_server.log"
max_size: "10MB"
backup_count: 5
# Security Configuration
security:
cors:
enabled: true
allow_origins: ["*"]
allow_methods: ["GET", "POST", "PUT", "DELETE", "OPTIONS"]
allow_headers: ["*"]
allow_credentials: true
rate_limiting:
enabled: false
requests_per_minute: 60
# Performance Configuration
performance:
max_concurrent_requests: 10
request_timeout: 300
keep_alive_timeout: 5
cache:
enabled: false
ttl: 3600 # 1 hour
max_size: 1000
# Monitoring Configuration
monitoring:
health_check:
enabled: true
interval: 30 # seconds
metrics:
enabled: false
prometheus_port: 9090
profiling:
enabled: false
# Development Configuration
development:
hot_reload: false
auto_restart: false
debug_toolbar: false
# Tools Configuration
tools:
process_pdf_smart:
enabled: true
timeout: 300
max_retries: 3
extract_pdf_text:
enabled: true
timeout: 60
max_retries: 2
ocr_pdf_pages:
enabled: true
timeout: 600
max_retries: 2
get_pdf_info:
enabled: true
timeout: 30
max_retries: 1
batch_process_pdfs:
enabled: true
timeout: 1800 # 30 minutes
max_retries: 1
# Environment Variables
environment:
PYTHONPATH: "."
MCP_SERVER_HOST: "${server.host}"
MCP_SERVER_PORT: "${server.port}"
OCR_LANGUAGE: "${ocr.default_language}"
OCR_DPI: "${ocr.default_dpi}"
LOG_LEVEL: "${logging.level}"
DEBUG: "${server.debug}"
# Deployment Configuration
deployment:
docker:
image: "ocr-pdf-mcp:1.0.0"
ports:
- "8000:8000"
volumes:
- "./data:/app/data"
- "./logs:/app/logs"
environment:
- "MCP_SERVER_HOST=0.0.0.0"
- "MCP_SERVER_PORT=8000"
kubernetes:
namespace: "mcp-servers"
replicas: 2
resources:
requests:
cpu: "100m"
memory: "256Mi"
limits:
cpu: "500m"
memory: "1Gi"
