Mnemosyne MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_entitiesB | Create multiple new entities in your Memento MCP knowledge graph memory system |
| create_relationsB | Create multiple new relations between entities in your Memento MCP knowledge graph memory. Relations should be in active voice |
| add_observationsB | Add new observations to existing entities in your Memento MCP knowledge graph memory |
| delete_entitiesA | Delete multiple entities and their associated relations from your Memento MCP knowledge graph memory |
| delete_observationsB | Delete specific observations from entities in your Memento MCP knowledge graph memory |
| delete_relationsB | Delete multiple relations from your Memento MCP knowledge graph memory |
| get_relationB | Get a specific relation with its enhanced properties from your Memento MCP knowledge graph memory |
| update_relationB | Update an existing relation with enhanced properties in your Memento MCP knowledge graph memory |
| read_graphA | Read the entire Memento MCP knowledge graph memory system |
| search_nodesB | Search for nodes in your Memento MCP knowledge graph memory based on a query |
| open_nodesB | Open specific nodes in your Memento MCP knowledge graph memory by their names |
| semantic_searchB | Search for entities semantically using vector embeddings and similarity in your Memento MCP knowledge graph memory |
| get_entity_embeddingA | Get the vector embedding for a specific entity from your Memento MCP knowledge graph memory |
| get_entity_historyA | Get the version history of an entity from your Memento MCP knowledge graph memory |
| get_relation_historyB | Get the version history of a relation from your Memento MCP knowledge graph memory |
| get_graph_at_timeA | Get your Memento MCP knowledge graph memory as it existed at a specific point in time |
| get_decayed_graphA | Get your Memento MCP knowledge graph memory with confidence values decayed based on time |
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 17 tools
Most tools have clear distinct purposes, but search_nodes, semantic_search, and open_nodes all relate to finding nodes with subtle differences; similarly, read_graph, get_graph_at_time, and get_decayed_graph are distinct temporal/decay views but could be confused by an agent.
The naming is largely consistent with verb_noun snake_case (e.g., create_entities, delete_relations, add_observations). Minor deviations include 'read_graph' vs 'get_graph_at_time' and 'search_nodes' vs 'semantic_search', which break the pattern slightly but remain readable.
17 tools is slightly above the typical 3-15 sweet spot, but the knowledge graph domain with history, embeddings, and temporal views justifies the additional tools. It feels a bit heavy but not excessive.
The surface covers creation, deletion, and relation management well, but there are notable gaps: no update_entities or update_observations, and no explicit single-entity getter (open_nodes is name-based rather than ID-based). These gaps force agents to work around the incomplete CRUD lifecycle.