Memory
Knowledge graph-based persistent memory system
Send to Your Agent
Copy this prompt and paste it into Claude, Cursor, or any MCP client to install instantly.
Install the Memory MCP server for me.
Server: Memory
Description: Knowledge graph-based persistent memory system
Install command: npx -y @modelcontextprotocol/server-memory
Environment variables needed:
- MEMORY_FILE_PATH: Path to the memory file (optional, defaults to memory.json in working directory)
GitHub: https://github.com/modelcontextprotocol/servers/tree/main/src/memory
Please install this MCP server and confirm when ready.Paste into any AI agent with MCP support — works with Claude Desktop, Cursor, Cline, and more.
Quick Install
Config file: ~/Library/Application Support/Claude/claude_desktop_config.json
- Open Claude Desktop app
- Go to Settings → Developer → Edit Config
- Paste the config below into the file
- Restart Claude Desktop
{
"mcpServers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}Add this to your ~/Library/Application Support/Claude/claude_desktop_config.json
Installation Methods
npx -y @modelcontextprotocol/server-memorydocker run -i --rm mcp/memoryTools (9)
create_entities Create new entities in the knowledge graph with type and observations
create_relations Create directed relations between entities
add_observations Add new observations to existing entities
delete_entities Remove entities and their relations from the knowledge graph
delete_observations Remove specific observations from entities
delete_relations Remove relations between entities
read_graph Read the entire knowledge graph
search_nodes Search for entities by name or observation content
open_nodes Open specific entities by name to view their details
Environment Variables
MEMORY_FILE_PATH OptionalPath to the memory file (optional, defaults to memory.json in working directory)
/path/to/memory.json| Name | Description | Required | Example |
|---|---|---|---|
| MEMORY_FILE_PATH | Path to the memory file (optional, defaults to memory.json in working directory) | Optional | /path/to/memory.json |
Compatibility
About
A Model Context Protocol server that provides persistent memory using a local knowledge graph. This lets Claude and other MCP clients remember information about the user across conversations.
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
Example:
{
"name": "John_Smith",
"entityType": "person",
"observations": ["Speaks fluent Spanish", "Works as a software engineer"]
}
Relations
Relations define directed connections between entities. They are always stored in active voice.
Example:
{
"from": "John_Smith",
"to": "Anthropic",
"relationType": "works_at"
}
Observations
Observations are discrete pieces of information about an entity. They are:
- Stored as strings
- Attached to specific entities
- Can be added or removed independently
- Should be atomic (one fact per observation)
Use Cases
- User preference memory — Remember coding style, communication preferences
- Project context — Track project history, decisions, and stakeholders
- Relationship tracking — Maintain organizational charts and connections
- Long-term learning — Build up knowledge about domains over time
Related Resources
Knowledge Graph Builder
PromptExtract entities, relationships, and semantic connections from unstructured text to build structured knowledge graphs for search, discovery, and data integration.
Sequential Thinking
MCP ServerDynamic and reflective problem-solving through thought sequences
3D Printing Optimizer
SkillOptimize 3D models for additive manufacturing considering orientation, supports, infill, and material properties.
Artificial Intelligence
GlossaryThe broad field of creating machines that can perform tasks requiring human-like intelligence, such as reasoning, learning, and perception.
Chart
MCP ServerA visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.
Compare LLM Pricing
This server works with Claude, GPT-4o, and other models. Compare API costs side-by-side to find the cheapest option for your workflow.