---
title: "Memory MCP Server for ToolPiper · ModelPiper"
description: "Knowledge-graph backed persistent memory across chats. Memory keeps a JSONL knowledge graph on disk and gives the model nine tools to read and write it. Entities have a name, a type (`person`, `project`, `event`), and a"
canonical: "https://modelpiper.com/mcp-tools/memory"
---

# Memory MCP Server for ToolPiper · ModelPiper

> Knowledge-graph backed persistent memory across chats. Memory keeps a JSONL knowledge graph on disk and gives the model nine tools to read and write it. Entities have a name, a type (`person`, `project`, `event`), and a

M

# Memory MCP Server

✓ verified

Knowledge-graph backed persistent memory across chats.

Install Memory in ToolPiper

Don't have ToolPiper? We'll take you to the download.

[Open repository →](https://github.com/modelcontextprotocol/servers/tree/main/src/memory)

Publisher

[Anthropic](https://github.com/modelcontextprotocol/servers)

License

MIT

Transport

Local subprocess

Tools

5

## What this server does

Memory keeps a JSONL knowledge graph on disk and gives the model nine tools to read and write it. Entities have a name, a type (\`person\`, \`project\`, \`event\`), and a flat list of string observations. Relations connect entities directionally in active voice (\`works\_at\`, \`depends\_on\`). That is the entire model: nodes, edges, and atomic facts attached to nodes. Default storage is \`memory.jsonl\` next to the server binary; override with \`MEMORY\_FILE\_PATH\` to put it somewhere durable. The graph survives restarts because it is just a file. Two reads are worth knowing about. \`search\_nodes\` matches against names, types, and observation content in one pass, so the model can ask 'what do I know about Acme?' and get the entity plus its relations back. \`open\_nodes\` retrieves specific entities by name along with the edges between them. Deletions cascade: removing an entity strips its relations too. Boot it with \`npx -y @modelcontextprotocol/server-memory\` and you have everything above. No schema migration, no auth, no setup beyond pointing it at a file. The interesting part is the system prompt you pair it with. The upstream README ships a sample prompt that flags \`Basic Identity\`, \`Behaviors\`, \`Preferences\`, \`Goals\`, and \`Relationships\` as the categories to capture. Drop that into custom instructions and the model populates the graph as you talk to it. Without that nudge, the model rarely writes anything; with it, the file grows quickly. Curate the prompt to match what you actually want remembered.

## Tools included

-   create\_entities
    
    Add nodes to the memory knowledge graph.
    
-   create\_relations
    
    Connect entities with named relations.
    
-   add\_observations
    
    Attach observations to an entity.
    
-   search\_nodes
    
    Search the knowledge graph by query.
    
-   read\_graph
    
    Read the entire knowledge graph.
    

The authoritative list comes from the server's tools/list at runtime. This catalog entry may lag the upstream until the next ToolPiper release.

## Install in ToolPiper

ToolPiper handles the JSON configuration. Click Install, fill in any required tokens, and the server is ready in your chat.

Install Memory in ToolPiper

Don't have ToolPiper? We'll take you to the download.

## Install in another client

Install in another MCP client (Claude Desktop, Cursor, Continue, Cline)

Claude Desktop Cursor Continue Cline

Add this to ~/Library/Application Support/Claude/claude\_desktop\_config.json.

```
{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}
```

Copy

## Example prompts

-   "Add an entity for my coworker Mark: works at Acme, lives in Berlin, prefers async."
    
    Copy
-   "What do you remember about the Acme migration project?"
    
    Copy
-   "Search the graph for everyone connected to the auth-rewrite project."
    
    Copy
-   "Remove the observation 'lives in NYC' from John\_Smith. He moved last month."
    
    Copy

## Security notes

Local-only. No network calls, no auth. The graph is a JSONL file in plaintext, no encryption. Anything the model writes (names, emails, opinions about people) lands there as-is, so do not point \`MEMORY\_FILE\_PATH\` at a synced folder unless you have thought about who else reads it. The system prompt determines what gets captured: an aggressive 'remember everything' prompt produces a noisier file with more PII in it. Curate the prompt, not the file after the fact. The Docker installation persists the graph to a named volume (\`claude-memory\`); the README warns that updating the image can overwrite an older volume's \`index.js\`, so back up before upgrading.

## Related tools

-   [
    
    S
    
    ### Sequential Thinking
    
    ✓ verified
    
    Dynamic, reflective problem-solving through thought sequences.
    
    AI ToolingLocal subprocess1 tool
    
    
    
    
    
    ](/mcp-tools/sequential-thinking)

[← Back to all MCP tools](/mcp-tools)