MCP AI Memory
by scanadi
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_TTL | No | Cache TTL in seconds | 3600 |
| LOG_LEVEL | No | Logging level | info |
| REDIS_URL | No | Redis connection string (optional) | |
| DATABASE_URL | No | PostgreSQL connection string | |
| MEMORY_DB_URL | No | PostgreSQL connection string | |
| EMBEDDING_MODEL | No | Transformers.js model | Xenova/all-MiniLM-L6-v2 |
| BULL_CONCURRENCY | No | Worker concurrency | 3 |
| MAX_CONTENT_SIZE | No | Maximum content size | 1048576 |
| MEMORY_CACHE_TTL | No | 2 hours for individual memories | 7200 |
| SEARCH_CACHE_TTL | No | 1 hour for search results | 3600 |
| ENABLE_REDIS_CACHE | No | Enable Redis caching | true |
| EMBEDDING_CACHE_TTL | No | 24 hours for embeddings | 86400 |
| DEFAULT_SEARCH_LIMIT | No | Default search limit | 20 |
| MIN_SIMILARITY_SCORE | No | Min similarity threshold | 0.5 |
| MAX_MEMORIES_PER_QUERY | No | Max results per search | 10 |
| ENABLE_ASYNC_PROCESSING | No | Enable background job processing | true |
| DEFAULT_SIMILARITY_THRESHOLD | No | Default similarity threshold | 0.7 |
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 | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues