SAM
by PiGrieco
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging verbosity level | INFO |
| CURSOR_MODE | No | Platform-specific optimizations for Cursor IDE | true |
| ENVIRONMENT | No | Current environment mode | development |
| MONGODB_URI | No | Database connection for persistent memory storage | mongodb://localhost:27017 |
| SERVER_MODE | No | Architecture mode (universal for modern unified server) | universal |
| ML_MODEL_TYPE | No | Type of ML model (huggingface for transformer models) | huggingface |
| EMBEDDING_MODEL | No | Lightweight, fast embedding model | all-MiniLM-L6-v2 |
| ML_TRIGGER_MODE | No | Combines ML model + deterministic rules | hybrid |
| MEMORY_THRESHOLD | No | Memory importance filtering (70%) | 0.7 |
| MONGODB_DATABASE | No | Database name for memory collections | mcp_memory_dev |
| PRELOAD_ML_MODEL | No | Loads ML model at startup for faster response times | true |
| TRIGGER_THRESHOLD | No | General trigger activation sensitivity (15%) | 0.15 |
| EMBEDDING_PROVIDER | No | Vector embedding engine | sentence_transformers |
| SEMANTIC_THRESHOLD | No | Context similarity matching (80%) | 0.8 |
| ML_RETRAIN_INTERVAL | No | Retrain model after 50 new samples | 50 |
| ML_TRAINING_ENABLED | No | Enables model improvement over time | true |
| AUTO_TRIGGER_ENABLED | No | Enables automatic memory operations without user commands | true |
| SIMILARITY_THRESHOLD | No | Semantic search matching threshold (30%) | 0.3 |
| BEHAVIOR_HISTORY_LIMIT | No | Maximum behavior samples to store | 1000 |
| HUGGINGFACE_MODEL_NAME | No | Specific SAM model with 99.56% accuracy | PiGrieco/mcp-memory-auto-trigger-model |
| USER_BEHAVIOR_TRACKING | No | Learn from user patterns | true |
| ML_CONFIDENCE_THRESHOLD | No | Main ML model confidence (70% threshold) | 0.7 |
| MAX_CONVERSATION_HISTORY | No | Context window for analysis | 10 |
| FEATURE_EXTRACTION_TIMEOUT | No | ML processing timeout (5 seconds) | 5.0 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/PiGrieco/mcp-memory-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server