MCP server for enabling memory for Claude through a knowledge graph
MCP Memory Domain Knowledge MCP server exists for a simple reason — assistants are far more useful when they can act on MCP Memory Domain Knowledge directly instead of describing what you should do. MCP server for enabling memory for Claude through a knowledge graph.
forked https://github.com/modelcontextprotocol/servers/tree/main
Installation goes through your MCP client rather than a global install: point it at with on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once MCP Memory Domain Knowledge is connected, these are the calls the assistant has available:
create_entities — Create multiple new entities in the knowledge graphInput — entities (array of objects)create_relations — Create multiple new relations between entitiesadd_observations — Add new observations to existing entitiesdelete_entities — Remove entities and their relationsdelete_observations — Remove specific observations from entitiesdelete_relations — Remove specific relations from the graphread_graph — Read the entire knowledge graphsearch_nodes — Search for nodes based on one or more keywordsSpace — separated keywords (e.g., "budget utility")Subdomains — Observation contentCase-insensitive — Partial word matchingYou will need one environment variable: MEMORY_FILE_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Memory Domain Knowledge's toolset — create_entities, Input, create_relations and 11 more — is a fair guide to whether it matches your workflow. It is maintained by yodakeisuke; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| create_entities | Create multiple new entities in the knowledge graph |
| Input | entities (array of objects) |
| create_relations | Create multiple new relations between entities |
| add_observations | Add new observations to existing entities |
| delete_entities | Remove entities and their relations |
| delete_observations | Remove specific observations from entities |
| delete_relations | Remove specific relations from the graph |
| read_graph | Read the entire knowledge graph |
| search_nodes | Search for nodes based on one or more keywords |
| Space | separated keywords (e.g., "budget utility") |
| Subdomains | Observation content |
| Case-insensitive | Partial word matching |
| open_nodes | Retrieve specific nodes by name |
| Returns | - Requested entities |
{
"mcpServers": {
"memory": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/memory"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| MEMORY_FILE_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.