Brain

Provides a memory management MCP server with short-term and long-term memory, plus thinking-process tools for AI workflows.

javascript

1

GitHub Stars

javascript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ddguan2010-brain-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "digital-brain-mcp"
      ],
      "env": {
        "NODE_ENV": "production",
        "BRAIN_MCP_STORAGE_PATH": "./memory_data",
        "BRAIN_MCP_AUTO_SAVE_INTERVAL": "300000"
      }
    }
  }
}

Brain-MCP provides a comprehensive memory and thinking management system for AI, enabling short-term and long-term memory, along with structured thinking processes. It helps preserve context across conversations, form meaningful memory associations, and manage complex thought chains for more capable and coherent AI interactions.

How to use

To use Brain-MCP, run the MCP server locally and connect your MCP client to interact with memory and thinking tools. You can add, search, and link memories, then design and manage thought chains to reach conclusions with traceable reasoning.

How to install

Prerequisites: Node.js version 18.0.0 or higher and an MCP client like Claude Desktop, Cursor, or VSCode.

Install and run Brain-MCP locally by following these steps.

git clone https://github.com/DDguan2010/brain-mcp.git
cd brain-mcp
npm install
npm run build
npm start

Configuration and usage notes

Configure the MCP server to use a memory storage path. The following configuration is used to run Brain-MCP with a local storage directory.

{
  "mcpServers": {
    "brain": {
      "command": "npx",
      "args": ["-y", "digital-brain-mcp"],
      "env": {
        "BRAIN_MCP_STORAGE_PATH":"./memory_data"
      }
    }
  }
}

Available tools

addShortTermMemory

Add a piece of information to the short-term memory cache.

getShortTermMemory

Retrieve all short-term memories in order of recency.

clearShortTermMemory

Clear all entries from the short-term memory cache.

addLongTermMemory

Create a new persistent memory node with optional associations.

getLongTermMemory

Retrieve a long-term memory node by its ID and its links.

searchLongTermMemory

Search long-term memories by keyword or phrase.

updateLongTermMemory

Update memory content or its associations.

deleteLongTermMemory

Delete a memory node and its links.

getAssociations

Get direct associations for a memory node.

startThoughtProcess

Start a new thinking chain for problem solving.

addThought

Add a thinking node to the current chain.

branchThought

Create a branch from an existing thinking node.

evaluateThought

Evaluate and adjust the confidence of a thought.

completeThoughtProcess

Finalize a thinking chain and store the conclusion.

getCurrentThoughtChain

View the current state of a thinking chain.

pauseThinking

Pause an active thinking process.

resumeThinking

Resume a paused thinking process.

switchCognitiveMode

Change the cognitive mode for the task at hand.

getOptimalModeForTask

Recommend the best cognitive mode for a given task.

getThinkingProgress

Retrieve progress statistics for thinking processes.

getActiveChains

List all active thinking chains.

getThinkingStats

Retrieve overall statistics for thinking processes.

saveMemory

Manually persist memory data to disk.

getMemoryStats

Retrieve statistics about the memory system.