Memory MCP Server
by gregpriday
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | Yes | OpenAI API key for embeddings and LLM orchestration | |
| MEMORY_LOG_LEVEL | No | Log level: debug, info, warn, error (default: info) | |
| MEMORY_DEBUG_MODE | No | Debug flags (true/false) | |
| MEMORY_LOG_FORMAT | No | Log format: json, pretty (default: pretty) | |
| MEMORY_ACTIVE_PROJECT | Yes | Active project identifier | |
| MEMORY_EMBEDDING_MODEL | Yes | Embedding model (determines vector dimensions). Default: text-embedding-3-small | text-embedding-3-small |
| MEMORY_DB_SLOW_QUERY_MS | No | Slow query threshold in milliseconds (default: 200) | |
| MEMORY_DEBUG_OPERATIONS | No | Debug operations (true/false) | |
| MEMORY_DEBUG_REPOSITORY | No | Debug repository (true/false) | |
| MEMORY_DEBUG_VALIDATION | No | Debug validation (true/false) | |
| MEMORY_CHUNK_CHAR_LENGTH | No | Chunk character length (default: 16000) | |
| MEMORY_CHUNK_CHAR_OVERLAP | No | Chunk character overlap (default: 2000) | |
| MEMORY_MCP_SYSTEM_MESSAGE | No | Host/system context (inline text or file path) | |
| MEMORY_MAX_CHUNKS_PER_FILE | No | Max chunks per file (default: 24) | |
| MEMORY_REFINE_ALLOW_DELETE | No | Allow delete in refinement (true/false) | |
| MEMORY_EMBEDDING_DIMENSIONS | No | Embedding dimensions (auto-detected from model, manual override available) | |
| MEMORY_ACCESS_PRIORITY_BOOST | No | Access priority boost (default: 0.01) | |
| MEMORY_ACCESS_TRACKING_TOP_N | No | Access tracking top N (default: 3) | |
| MEMORY_DEBUG_ACCESS_TRACKING | No | Debug access tracking (true/false) | |
| MEMORY_MAX_MEMORIES_PER_FILE | No | Max memories per file (default: 50) | |
| MEMORY_QUERY_EXPANSION_COUNT | No | Query expansion count (default: 2) | |
| MEMORY_REFINE_DEFAULT_BUDGET | No | Default refinement budget (default: 100) | |
| MEMORY_ACCESS_TRACKING_ENABLED | No | Access tracking enabled (true/false) | |
| MEMORY_QUERY_EXPANSION_ENABLED | No | Query expansion enabled (true/false) | |
| MEMORY_POSTGRES_PROJECT_REGISTRY | Yes | Path to the project registry JSON file | |
| MEMORY_LARGE_FILE_THRESHOLD_BYTES | No | Large file threshold bytes (default: 262144) |
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
ActivityNo data
ResponsivenessNo issues