MemoryMCP
by solidlime
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PERSONA | No | Default persona name (overrides NOUS_DEFAULT_PERSONA). | |
| NOUS_TIMEZONE | No | Timezone. | Asia/Tokyo |
| NOUS_DATA_ROOT | No | Data storage root directory (all sub-paths auto-derived). | ./data |
| NOUS_LOG_LEVEL | No | Log level. | INFO |
| NOUS_QDRANT__URL | No | Qdrant connection URL. | http://localhost:6333 |
| NOUS_SERVER__HOST | No | Bind address. | 0.0.0.0 |
| NOUS_SERVER__PORT | No | HTTP port. | 26262 |
| NOUS_DEFAULT_PERSONA | No | Default persona name. | default |
| NOUS_RERANKER__MODEL | No | Reranker model. | hotchpotch/japanese-reranker-xsmall-v2 |
| NOUS_EMBEDDING__MODEL | No | Embedding model. | cl-nagoya/ruri-v3-30m |
| NOUS_MEMORAG__ENABLED | No | Enable MemoRAG context snapshot. | true |
| NOUS_SANDBOX__ENABLED | No | Enable sandbox code execution. | true |
| NOUS_SANDBOX__TIMEOUT | No | Code execution timeout in seconds. | 30 |
| NOUS_SANDBOX__PROVIDER | No | Sandbox provider. | llm_sandbox |
| NOUS_FORGETTING__ENABLED | No | Enable Ebbinghaus forgetting curve. | true |
| NOUS_SANDBOX__DOCKER_HOST | No | Docker host URL (empty = auto-detect socket). | |
| NOUS_SANDBOX__HOST_DATA_ROOT | No | Host-side data directory absolute path (for sibling-container persistence). | |
| NOUS_FORGETTING__MIN_STRENGTH | No | Minimum memory strength. | 0.01 |
| NOUS_MEMORY_ENRICHMENT__MODEL | No | LLM model for enrichment. | openai/gpt-4o-mini |
| NOUS_MEMORY_ENRICHMENT__API_KEY | No | LLM API key for enrichment. | |
| NOUS_MEMORY_ENRICHMENT__ENABLED | No | Enable LLM enrichment (importance/relation extraction) on memory creation. | true |
| NOUS_MEMORY_ENRICHMENT__BASE_URL | No | LLM API base URL. | https://openrouter.ai/api/v1 |
| NOUS_MEMORY_ENRICHMENT__PROVIDER | No | LLM provider for enrichment. | openrouter |
| NOUS_MEMORY_ENRICHMENT__MIN_CHARS | No | Minimum characters to skip enrichment. | 10 |
| NOUS_MEMORAG__CLUE_GENERATION_ENABLED | No | Enable LLM-based query clue generation. | false |
| NOUS_FORGETTING__DECAY_INTERVAL_SECONDS | No | Decay worker execution interval in seconds. | 3600 |
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
ActivityActive
ResponsivenessNo issues