memdb
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMDB_PATH | No | Path to the SQLite database file. Set to `:memory:` for an in-memory database. | .memdb/memory.db |
| MEMDB_LOG_LEVEL | No | Logging verbosity level: error, warn, or info. | info |
| MEMDB_TOOL_TIMEOUT_MS | No | Tool execution timeout in milliseconds (non-negative integer). | 15000 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| store_memoryB | Store a new memory with tags |
| store_memoriesA | Store multiple memories in a single batch operation. Returns per-item results with partial success support. |
| get_memoryC | Retrieve memory by hash |
| delete_memoryC | Delete by hash |
| delete_memoriesA | Delete multiple memories by hash in a single batch operation. Returns per-item results with partial success support. |
| update_memoryA | Update memory content. Returns new hash since content change affects the hash. |
| search_memoriesB | Search memories by content and tags |
| recallA | Search for memories and traverse relationships to return a connected graph cluster. Use this for deeper context retrieval that follows knowledge graph connections. |
| create_relationshipA | Link two memories with a typed relationship. Creates a knowledge graph edge between memories. |
| get_relationshipsA | Get all relationships for a memory. Returns linked memories with relationship types. |
| delete_relationshipA | Remove a relationship between two memories. |
| memory_statsA | Database statistics and health |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Tools are mostly distinct: CRUD operations, batch variants, search, and relationship operations each have clear roles. The only mild ambiguity is between search_memories and recall, though recall's relationship traversal is explicitly described.
Most tools follow a clear verb_noun pattern like store_memory, get_memory, delete_memory, and create_relationship. Minor deviations are 'recall' and 'memory_stats', which are still readable but break the otherwise consistent convention.
12 tools is well-scoped for a memory server with knowledge graph features. Each tool covers a distinct operation without bloat or redundancy.
The memory lifecycle is well covered with single and batch creates/deletes, retrieval, update, search, and stats. Minor gaps include no explicit list-all operation and no update operation for relationships, but these are workable via search and delete/recreate.