Mnemo MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DB_PATH | No | SQLite database path | ~/.mnemo-mcp/memories.db |
| LOG_LEVEL | No | Log verbosity | INFO |
| LLM_MODELS | No | LLM chain for graph extraction / importance / compression; empty disables those features | |
| PUBLIC_URL | No | Public URL for HTTP multi-user remote mode | |
| SYNC_FOLDER | No | Google Drive folder name | mnemo-mcp |
| LLM_API_BASE | No | Custom OpenAI-compatible endpoint for LLM (SSRF-guarded) | |
| RERANK_TOP_N | No | Number of reranked results to keep | 10 |
| SYNC_ENABLED | No | Enable Google Drive multi-machine sync | true |
| MCP_TRANSPORT | No | Transport mode (stdio or http) | stdio |
| MNEMO_DB_PATH | No | Alias for DB_PATH | |
| RERANK_MODELS | No | Rerank chain, e.g. jina_ai/jina-reranker-v3,cohere/rerank-v3.5 | |
| SYNC_INTERVAL | No | Auto-sync interval in seconds (0 = manual only) | 300 |
| COHERE_API_KEY | No | API key for Cohere models (cohere/ prefix) | |
| EMBEDDING_DIMS | No | Embedding dimensions (0 = auto-detect) | 768 |
| GEMINI_API_KEY | No | API key for Gemini models (gemini/ prefix) | |
| OPENAI_API_KEY | No | API key for OpenAI models (openai/ or bare) | |
| RERANK_ENABLED | No | Enable reranking of fused results | true |
| ARCHIVE_ENABLED | No | Enable importance x recency soft-archive sweeps | true |
| DEDUP_THRESHOLD | No | Similarity above which a new memory is a duplicate | 0.9 |
| JINA_AI_API_KEY | No | API key for Jina AI models (jina_ai/ prefix) | |
| KG_AUTO_ENABLED | No | Auto-extract entities + relations on capture | false |
| RERANK_API_BASE | No | Custom OpenAI-compatible endpoint for reranking (SSRF-guarded) | |
| EMBEDDING_MODELS | No | Embedding chain, e.g. jina_ai/jina-embeddings-v5-text-small,gemini/gemini-embedding-001 | |
| ARCHIVE_AFTER_DAYS | No | Age before a memory is eligible for archive | 90 |
| EMBEDDING_API_BASE | No | Custom OpenAI-compatible endpoint for embedding (SSRF-guarded) | |
| CAPTURE_AUTO_ENABLED | No | Opt-in PostToolUse hook to hint memory-commit after writing to specific files | false |
| GOOGLE_DRIVE_CLIENT_ID | No | OAuth client ID required for sync | |
| RECENCY_HALF_LIFE_DAYS | No | Half-life for temporal decay scoring | 7 |
| REINDEX_ON_MODEL_CHANGE | No | Re-embed on model change (safe-by-default guard blocks boot on mismatch) | false |
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
ActivityStale
ResponsivenessNo issues