Skip to main content
Glama

MCP Memory Server

by hannesnortje
config.example.yaml•1.51 kB
# MCP Memory Server Configuration # This file demonstrates the YAML configuration capabilities server: name: "memory-server" version: "1.0.0" description: "Memory management server for AI agents using Qdrant vector database" logging: level: "INFO" # DEBUG, INFO, WARNING, ERROR, CRITICAL format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s" file: null # Optional log file path qdrant: mode: "local" # local, remote, cloud host: "localhost" port: 6333 api_key: null # Required for cloud mode timeout: 60 # Docker settings (for local mode) docker_image: "qdrant/qdrant:latest" container_name: "qdrant" # Timeouts startup_timeout: 15 health_check_timeout: 5 embedding: model_name: "all-MiniLM-L6-v2" dimension: 384 device: "cpu" # or "cuda" for GPU acceleration cache_folder: null markdown: chunk_size: 900 chunk_overlap: 200 recursive_processing: true # AI enhancement settings ai_enhancement_enabled: true ai_analysis_depth: "standard" # basic, standard, deep ai_content_optimization: true policy: directory: "./policy" rule_id_pattern: "^[A-Z]+-\\d+$" validation_strict: true hash_algorithm: "sha256" memory: type_confidence_threshold: 0.6 suggestion_enabled: true deduplication: similarity_threshold: 0.85 near_miss_threshold: 0.80 logging_enabled: true diagnostics_enabled: true error_handling: retry_attempts: 3 base_delay: 1.0 max_delay: 30.0 exponential_base: 2.0 jitter_enabled: true

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/hannesnortje/MCP'

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