Memory MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
npm install
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add memory-mcp-server -- node "<FULL_PATH_TO_MCP_MEMORY_SERVER>/dist/index.js"

Replace <FULL_PATH_TO_MCP_MEMORY_SERVER>/dist/index.js with the actual folder you prepared in step 1.

README.md

Store and retrieve memories across OpenCode sessions.

Memory MCP Server

Store and retrieve memories across OpenCode sessions.

Setup

cd /home/naresh/Projects/mcp-memory-server
npm install

Usage

Start the server

npm start

Memories are saved to: ~/Documents/memory-mcp/memories.json

For OpenCode Integration

Add to your OpenCode config (~/.config/opencode/opencode.jsonc):

{
  "mcpServers": {
    "memory": {
      "command": "node",
      "args": ["/home/naresh/Projects/mcp-memory-server/server.js"]
    }
  }
}

Tools

store_memory

Store a new memory.

Input:

  • content: The memory content (required)
  • type: Type of memory - preference, context, decision, learning (required)
  • tags: Array of tags (optional)
  • namespace: Namespace for organization (default: global)

Example:

{
  "content": "Always use TypeScript, prefer Tailwind CSS",
  "type": "preference",
  "tags": ["typescript", "css", "ui"],
  "namespace": "voice-assistant"
}

search_memory

Search memories by query, type, tags, or namespace.

Input:

  • query: Search in content and tags (optional)
  • type: Filter by memory type (optional)
  • tags: Filter by tags (optional)
  • namespace: Filter by namespace (optional)

get_memory

Retrieve a memory by ID.

Input:

  • id: The memory ID (required)

update_memory

Update an existing memory by ID.

Input:

  • id: The memory ID (required)
  • content: New content (optional)
  • type: New type (optional)
  • tags: New tags (optional)
  • namespace: New namespace (optional)

delete_memory

Delete a memory by ID.

Input:

  • id: The memory ID (required)

list_memories

List all memories, optionally filtered.

Input:

  • namespace: Filter by namespace (optional)
  • type: Filter by type (optional)

Memory Schema

{
  "id": "abc123",
  "content": "User prefers Tailwind CSS",
  "type": "preference",
  "tags": ["css", "tailwind"],
  "namespace": "voice-assistant",
  "createdAt": "2026-02-11T10:00:00.000Z",
  "updatedAt": "2026-02-11T10:00:00.000Z",
  "accessCount": 0
}

Tools (6)

store_memoryStore a new memory with content, type, tags, and namespace.
search_memorySearch memories by query, type, tags, or namespace.
get_memoryRetrieve a memory by ID.
update_memoryUpdate an existing memory by ID.
delete_memoryDelete a memory by ID.
list_memoriesList all memories, optionally filtered by namespace or type.

Configuration

claude_desktop_config.json
{"mcpServers": {"memory": {"command": "node", "args": ["/home/naresh/Projects/mcp-memory-server/server.js"]}}}

Try it

Store a new preference that I always prefer using Tailwind CSS for my projects.
Search for all memories tagged with 'typescript' in the 'voice-assistant' namespace.
List all my current decision memories to review past project choices.
Update the memory with ID 'abc123' to reflect my new preference for CSS modules.
Delete the memory with ID 'abc123' as it is no longer relevant.

Frequently Asked Questions

What are the key features of Memory MCP Server?

Persistent storage of user preferences, context, and decisions. Structured JSON-based memory management. Namespace and tag-based organization. Full CRUD operations for memory items. Search functionality across content and tags.

What can I use Memory MCP Server for?

Maintaining consistent coding style preferences across different AI sessions. Storing project-specific context to avoid repeating instructions. Tracking important design decisions made during development. Organizing learning notes by namespace for quick retrieval.

How do I install Memory MCP Server?

Install Memory MCP Server by running: npm install

What MCP clients work with Memory MCP Server?

Memory MCP Server works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Memory MCP Server docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare