memento-mcp-server
by jee1
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP/MCP server port (http-server fallback) | 9001 |
| DB_PATH | No | Path to the SQLite database file | ./data/memory.db |
| NODE_ENV | No | Node.js environment (development, production, etc.) | development |
| LOG_LEVEL | No | Logging level | info |
| GEMINI_API_KEY | No | Optional Gemini API key for embeddings | |
| OPENAI_API_KEY | No | Optional OpenAI API key for embeddings | |
| MCP_SERVER_PORT | No | HTTP/MCP server port (alias for PORT) | 9001 |
| MEMENTO_TOOLSET | No | Set to 'full' to expose all MCP tools in tools/list instead of the default set | |
| FORGET_THRESHOLD | No | Forgetting score threshold for triggering forgetting | 0.6 |
| TTL_SOFT_WORKING | No | TTL in days for soft-deleting working memories | 2 |
| TTL_SOFT_EPISODIC | No | TTL in days for soft-deleting episodic memories | 30 |
| TTL_SOFT_SEMANTIC | No | TTL in days for soft-deleting semantic memories | 180 |
| EMBEDDING_PROVIDER | No | Embedding provider: tfidf, lightweight, minilm, openai, gemini | minilm |
| ENABLE_PII_MASKING | No | Enable PII masking | true |
| TTL_SOFT_PROCEDURAL | No | TTL in days for soft-deleting procedural memories | 90 |
| CORS_ALLOWED_ORIGINS | No | Comma-separated allowed origins; empty disables cross-origin | |
| HARD_DELETE_THRESHOLD | No | Forgetting score threshold for hard delete | 0.8 |
| SOFT_DELETE_THRESHOLD | No | Forgetting score threshold for soft delete | 0.6 |
| MEMORY_REVIEW_STALE_DAYS | No | Minimum stale days for memory review candidates (integer >= 1) | 14 |
| MEMORY_REVIEW_MAX_BACKLOG | No | Skip new candidate selection if pending backlog exceeds this; 0 disables | 500 |
| CONSOLIDATION_BASELINE_PATH | No | Path to baseline snapshot | ./data/consolidation-baseline.json |
| CONSOLIDATION_SCORE_ENABLED | No | Enable Consolidation Score System | false |
| CONSOLIDATION_TEST_SEED_PATH | No | Path to test seed data file | ./data/consolidation-seed.json |
| MEMORY_REVIEW_MAX_CANDIDATES | No | Maximum number of memory review candidates (integer >= 1) | 50 |
| CONSOLIDATION_TEST_ITEM_COUNT | No | Benchmark test data size | 100 |
| MEMORY_REVIEW_CANDIDATE_DUE_DAYS | No | Days added to due_at by batch (1-366) | 14 |
| MEMORY_REVIEW_CANDIDATE_TTL_DAYS | No | Expire pending candidates older than this many days; 0 disables | 30 |
| MEMORY_REVIEW_IMPORTANCE_THRESHOLD | No | Minimum importance for memory review candidates (0-1) | 0.7 |
| MEMORY_REVIEW_CANDIDATES_INTERVAL_MS | No | Batch schedule interval in milliseconds; minimum 60000 | 86400000 |
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/jee1/memento'
If you have feedback or need assistance with the MCP directory API, please join our Discord server