A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Every conversation with an LLM starts from zero — the colleague with perfect amnesia. The Memory MCP server is the reference fix: a local knowledge graph where the assistant records entities (people, projects, preferences), relations between them ("Sarah leads the mobile project") and observations ("prefers concise updates"), all persisted to disk and searchable in later sessions.
The graph structure matters more than it first appears. Flat note-taking rots into an unsearchable pile; entities-and-relations stay navigable — ask about Sarah and the assistant traverses to her projects, her preferences, the decisions she was part of. Memory recall becomes structured lookup rather than needle-hunting.
What emerges with steady use is continuity. Tell your assistant once that your stack is Next.js with Postgres and it stops asking; mention your manager's name in March and it's known in August; decisions land in the graph and "why did we choose X?" pulls the recorded reasoning. The standard pattern adds a system-prompt instruction telling the model when to store and retrieve — most clients let you set this per-project — after which memory maintenance happens quietly in the background of normal conversation.
Storage is a JSONL file on your machine: private by default, trivially backed up, portable between clients, editable by hand if the graph learns something wrong. Like the other archived reference servers it's stable rather than evolving, and its simplicity is the appeal — persistent memory with no database, no embeddings service, no subscription. For most personal-assistant setups it's the right first memory layer.
Sarah Chen and Sarah (design) become two unrelated nodes that never connect, and nothing warns you.MEMORY_FILE_PATH to a synced or version-controlled folder. The file is newline-delimited JSON, so a git diff after a session reads as a plain list of what the assistant learned.delete_observations removes a single stale fact while leaving the entity and its relations intact — usually what you want when a preference changes rather than deleting the person.Stack, preferences, colleagues and context accumulate instead of resetting.
Choices and their reasoning recorded, retrievable months later.
People and projects linked so recall follows the connections.
| Tool | What it does |
|---|---|
| create_entities | Add people, projects, concepts to the graph |
| create_relations | Link entities ('Sarah' — 'leads' — 'mobile project') |
| add_observations | Attach facts to entities |
| search_nodes | Find relevant memories by query |
| open_nodes | Read specific entities with their relations |
| read_graph | Dump the full graph |
| delete_entities / delete_observations | Forget things deliberately |
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-memory"]
}
}
}Set MEMORY_FILE_PATH to control where the graph lives; pair with a system-prompt instruction about when to remember.
Node.js 18+. Storage is a local JSONL file; add a system-prompt memory policy for best results.
| Variable | Description | Required |
|---|---|---|
| MEMORY_FILE_PATH | Where the knowledge-graph JSONL file is storede.g. /Users/you/.mcp-memory/graph.jsonl | Optional |
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.
Alibaba Cloud Ops MCP Server is a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) server that provides seamless