Memento
Memento MCP provides LLMs with a persistent knowledge graph memory system built on Neo4j, enabling semantic retrieval, contextual recall, and temporal awareness through entities, relations, and vector embeddings. The server allows any MCP-compatible client to store and query long-term ontological memory with features including confidence-weighted relations, complete version history, and time-based decay of information confidence. It solves the problem of LLMs lacking persistent, structured memory across sessions by offering a scalable, high-performance backend for maintaining and retrieving contextual knowledge over time.
- GitHub stars
- 418
- tools
- 20
- last updated
- Mar 10, 2026
Tools
20 toolsPublic tool metadata for what this MCP can expose to an agent.
create_entitiesCreate multiple new entities in the knowledge graph
Create multiple new entities in the knowledge graph
No parameter schema in public metadata yet.
add_observationsAdd new observations to existing entities
Add new observations to existing entities
No parameter schema in public metadata yet.
delete_entitiesRemove entities and their relations
Remove entities and their relations
No parameter schema in public metadata yet.
delete_observationsRemove specific observations from entities
Remove specific observations from entities
No parameter schema in public metadata yet.
create_relationsCreate multiple new relations between entities with enhanced properties
Create multiple new relations between entities with enhanced properties
No parameter schema in public metadata yet.
get_relationGet a specific relation with its enhanced properties
Get a specific relation with its enhanced properties
No parameter schema in public metadata yet.
update_relationUpdate an existing relation with enhanced properties
Update an existing relation with enhanced properties
No parameter schema in public metadata yet.
delete_relationsRemove specific relations from the graph
Remove specific relations from the graph
No parameter schema in public metadata yet.
read_graphRead the entire knowledge graph
Read the entire knowledge graph
No parameter schema in public metadata yet.
search_nodesSearch for nodes based on query
Search for nodes based on query
No parameter schema in public metadata yet.
open_nodesRetrieve specific nodes by name
Retrieve specific nodes by name
No parameter schema in public metadata yet.
semantic_searchSearch for entities semantically using vector embeddings and similarity
Search for entities semantically using vector embeddings and similarity
No parameter schema in public metadata yet.
get_entity_embeddingGet the vector embedding for a specific entity
Get the vector embedding for a specific entity
No parameter schema in public metadata yet.
get_entity_historyGet complete version history of an entity
Get complete version history of an entity
No parameter schema in public metadata yet.
get_relation_historyGet complete version history of a relation
Get complete version history of a relation
No parameter schema in public metadata yet.
get_graph_at_timeGet the state of the graph at a specific timestamp
Get the state of the graph at a specific timestamp
No parameter schema in public metadata yet.
get_decayed_graphGet graph with time-decayed confidence values
Get graph with time-decayed confidence values
No parameter schema in public metadata yet.
diagnose_vector_searchInformation about the Neo4j vector index, embedding counts, and search functionality
Information about the Neo4j vector index, embedding counts, and search functionality
No parameter schema in public metadata yet.
force_generate_embeddingForces the generation of an embedding for a specific entity
Forces the generation of an embedding for a specific entity
No parameter schema in public metadata yet.
debug_embedding_configInformation about the current embedding service configuration
Information about the current embedding service configuration
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Memento MCP: A Knowledge Graph Memory System for LLMs
Memento MCP Logo
Scalable, high performance knowledge graph memory system with semantic retrieval, contextual recall, and temporal awareness. Provides any LLM client that supports the model context protocol (e.g., Claude Desktop, Cursor, Github Copilot) with resilient, adaptive, and persistent long-term ontological memory.
Core Concepts
Entities
Entities are the primary nodes in the knowledge graph. Each entity has:
- A unique name (identifier)
- An entity type (e.g., "person", "organization", "event")
- A list of observations
- Vector embeddings (for semantic search)
- Complete version history
Example:
{
"name": "John_Smith",
"entityType": "person",
"observations": ["Speaks fluent Spanish"]
}
Relations
Details
- Repository
- github.com/gannonh/memento-mcp
- Categories
- AI & LLM Tools, Documents & Knowledge
Related AI & LLM Tools MCP servers
View all
Massive.commassive-com/mcp_massiveProvides access to Massive.com data via an MCP server with four composable tools and in-memory DataFrame storage for SQL queries and analytics.332stars
Ultra MCPrealmikechong/ultra-mcp100x Your Claude Code, Gemini CLI, Cursor and/or any coding tools with MCP client support274stars
Mimirorneryd/mimirProvides a persistent graph-based memory and task management for AI agents with MCP API access and semantic search.273stars
Sanitysanity-io/agent-toolkitGives AI agents direct access to your Sanity projects and guidance for working with them0stars
Mcp Imageshinpr/mcp-imageAI image generation and editing with prompt optimization and quality presets187stars
Codegraphcodegraph-ai/codegraphSemantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.144stars