mcp/memory
A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.
Entities are the primary nodes in the knowledge graph. Each entity has:
Example:
{
"name": "John_Smith",
"entityType": "person",
"observations": ["Speaks fluent Spanish"]
}
Relations define directed connections between entities. They are always stored in active voice and describe how entities interact or relate to each other.
Example:
{
"from": "John_Smith",
"to": "Anthropic",
"relationType": "works_at"
}
Observations are discrete pieces of information about an entity. They are:
Example:
{
"entityName": "John_Smith",
"observations": [
"Speaks fluent Spanish",
"Graduated in 2019",
"Prefers morning meetings"
]
}
create_entities
entities
(array of objects)
name
(string): Entity identifierentityType
(string): Type classificationobservations
(string[]): Associated observationscreate_relations
relations
(array of objects)
from
(string): Source entity nameto
(string): Target entity namerelationType
(string): Relationship type in active voiceadd_observations
observations
(array of objects)
entityName
(string): Target entitycontents
(string[]): New observations to adddelete_entities
entityNames
(string[])delete_observations
deletions
(array of objects)
entityName
(string): Target entityobservations
(string[]): Observations to removedelete_relations
relations
(array of objects)
from
(string): Source entity nameto
(string): Target entity namerelationType
(string): Relationship typeread_graph
search_nodes
query
(string)open_nodes
names
(string[])Add this to your claude_desktop_config.json:
{
"mcpServers": {
"memory": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/memory"]
}
}
}
The prompt for utilizing memory depends on the use case. Changing the prompt will help the model determine the frequency and types of memories created.
Here is an example prompt for chat personalization. You could use this prompt in the "Custom Instructions" field of a Claude.ai Project.
Follow these steps for each interaction:
1. User Identification:
- You should assume that you are interacting with default_user
- If you have not identified default_user, proactively try to do so.
2. Memory Retrieval:
- Always begin your chat by saying only "Remembering..." and retrieve all relevant information from your knowledge graph
- Always refer to your knowledge graph as your "memory"
3. Memory
- While conversing with the user, be attentive to any new information that falls into these categories:
a) Basic Identity (age, gender, location, job title, education level, etc.)
b) Behaviors (interests, habits, etc.)
c) Preferences (communication style, preferred language, etc.)
d) Goals (goals, targets, aspirations, etc.)
e) Relationships (personal and professional relationships up to 3 degrees of separation)
4. Memory Update:
- If any new information was gathered during the interaction, update your memory as follows:
a) Create entities for recurring organizations, people, and significant events
b) Connect them to the current entities using relations
b) Store facts about them as observations
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
docker pull mcp/memory