Memory MCP Server

🧠 AI Memory System powered by MongoDB Atlas & Voyage AI - Autonomous memory management with zero manual work

Local serverstdioPython

What is the Memory MCP server?

Memory MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. 🧠 AI Memory System powered by MongoDB Atlas & Voyage AI - Autonomous memory management with zero manual work.

What you get

Experience the power of semantic code search and persistent AI memory

Setting it up

The server ships on npm as memory-engineering-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Memory is connected, these are the calls the assistant has available:

  • memory_engineering_init — Initialize project
  • memory_engineering_memory — Read/Update memories
  • memory_engineering_search — Semantic search
  • memory_engineering_sync — Sync code embeddings
  • memory_engineering_system — Health & diagnostics
  • Installation — The Installation tool exposed by this server
  • Debugging — The Debugging tool exposed by this server

Configuration and credentials

You will need 2 environment variables: MONGODB_URI, VOYAGE_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the memory mcp server does with a few real requests.

Choosing this one

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Memory's toolset — memory_engineering_init, memory_engineering_memory, memory_engineering_search and 4 more — is a fair guide to whether it matches your workflow. It is maintained by romiluz13; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
memory_engineering_initInitialize project
memory_engineering_memoryRead/Update memories
memory_engineering_searchSemantic search
memory_engineering_syncSync code embeddings
memory_engineering_systemHealth & diagnostics
InstallationThe Installation tool exposed by this server.
DebuggingThe Debugging tool exposed by this server.

How to install the Memory MCP server

{
  "mcpServers": {
    "memory-engineering-mcp": {
      "command": "npx",
      "args": ["memory-engineering-mcp"],
      "env": {
        "MONGODB_URI": "your-mongodb-atlas-uri",
        "VOYAGE_API_KEY": "your-voyage-api-key"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
MONGODB_URIConfiguration value read at startup.Optional
VOYAGE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Memory to memory engineering init.
  • Use Memory to memory engineering memory.
  • Use Memory to memory engineering search.

Frequently asked questions

It connects Memory to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (memory_engineering_init, memory_engineering_memory, memory_engineering_search, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Memory directly.