mcpField
M
modelbrain

modelbrain

Local
modelbrain.netMemory & Knowledge0Updated 1w ago
RepositoryVisit website

About modelbrain

modelbrain-mcp connects MCP clients to the ModelBrain desktop app running locally, providing a private memory layer for people who use multiple AI assistants. It locates and runs the app’s bundled MCP binary rather than including the ModelBrain engine.

Key features

  1. 01Connects to the local ModelBrain app
  2. 02Runs the app’s bundled MCP binary
  3. 03Provides memory tools for saving and retrieval
  4. 04Explains where to get ModelBrain if it is missing

Use cases

  1. 01Share local memory across multiple AI assistants
  2. 02Connect a running ModelBrain app to an MCP client
  3. 03Save, retrieve, or delete memories

MCP support

The package launches ModelBrain’s bundled MCP server over stdio and connects it to the local daemon. Documented tools include remember, recall, forget, expand, and connector_sync.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "net-modelbrain": {
      "command": "npx",
      "args": [
        "-y",
        "modelbrain-mcp"
      ]
    }
  }
}
Run commandnpx -y modelbrain-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmodelbrain-mcp0.1.3

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

modelbrain-mcp

Listed on mcpservers.org

A thin MCP stdio client for ModelBrain: the private memory layer for AI assistants: one memory for every assistant you use, kept on your own computer.

This package does not install or bundle ModelBrain. It connects to the ModelBrain desktop app already running on your machine. If ModelBrain is not installed, running this prints where to get it and exits, rather than failing silently.

Why a separate package

ModelBrain's own installed app already ships a binary, mcp_server, that speaks MCP over stdio and talks to the local ModelBrain daemon. This package finds that binary on the current machine and runs it. It exists so ModelBrain can be registered with the MCP Registry and the directories that list from it, with a reviewable package as the distribution target, while the actual engine stays out of this repository.

Requirements

  • macOS (Apple Silicon) or Windows (x64 or arm64)
  • ModelBrain installed

Use

Most MCP clients run a server with npx. Point your client's MCP config at:

{
  "mcpServers": {
    "modelbrain": {
      "command": "npx",
      "args": ["-y", "modelbrain-mcp"]
    }
  }
}

Claude Desktop, Claude Code and Cursor users do not need this: ModelBrain's own app registers itself with those clients directly. See modelbrain.net/docs for the full tool surface (remember, recall, forget, expand, connector_sync) and the connect guides for other clients.

License

MIT, for this wrapper package. ModelBrain itself is separate, proprietary software; see modelbrain.net for its own terms.

Security

See SECURITY.md.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.