Multi-agent Cognitive Processing Framework with MiniMax

MCP-Brain: Multi-agent Cognitive Processing Framework

A lightweight AI framework that runs locally on your machine using MiniMax API. Three specialized agents — Analyst, Creator, and Critic — collaborate through a structured cognitive pipeline to solve complex problems.

User Task
   │
   ▼
┌──────────┐   Analyst breaks it down
│ Analyst ├─────────────────────────┐
└──────────┘                       │
   │                                │
   ▼                                │
┌──────────┐   Creator drafts   ┌──────────┐
│ Creator  │◄──────────────────┤ Analyst  │
└──────────┘                    │ Context  │
   │                            └──────────┘
   │                                │
   ▼                                │
┌──────────┐   Critic evaluates  ┌──────────┐
│ Critic   │◄────────────────────┤ Creator  │
└──────────┘                     │ Draft    │
   │                            └──────────┘
   │                                │
   ▼                                │
┌──────────┐   Creator improves   ┌──────────┐
│ Creator  │◄────────────────────┤ Critic   │
└──────────┘                     │ Feedback │
   │                            └──────────┘
   │
   ▼
┌──────────┐   Critic final     ┌──────────┐
│ Critic   │◄──────eval─────────│ Improved │
└──────────┘                    │ Solution │
   │                            └──────────┘
   ▼
Final Solution + Evaluation

Features

  • Local-only — API key and data never leave your machine
  • Multi-agent cognition — mimics human collaborative problem-solving
  • Persistent memory — sessions saved to ~/.mcp/ for review
  • Simple CLImcp setup, mcp process, mcp sessions
  • Streaming support — stream responses token-by-token

Installation

# Download and run installer
curl -fsSL https://raw.githubusercontent.com/MC80s/mcp/main/install.sh | bash

Or manually install from source

git clone https://github.com/MC80s/mcp.gitcd mcpbash install.sh

Or install with pip

pip install mcp-brain


## Quick Start

```bash
# 1. Configure your MiniMax API key
mcp setup

# 2. Process your first task
mcp process "Design a logo for a tech startup called Quantum Leap"

# 3. View previous sessions
mcp sessions

# 4. Check config status
mcp status

How It Works

Step Agent Role
1 Analyst Breaks down the problem into components
2 Creator Generates an initial creative solution
3 Critic Evaluates the draft, identifies flaws
4 Creator Improves the solution based on critique
5 Critic Final evaluation and rating

Cost Estimation

MiniMax API is pay-per-use. Each task runs 5 agent calls.

Complexity Est. Cost
Simple task ~$0.02–0.05
Medium task ~$0.05–0.15
Complex task ~$0.15–0.30

No subscription fees. You control your usage.

Project Structure

mcp-brain/
├── src/mcp/
│   ├── minimax_client.py   # MiniMax API client
│   ├── agents.py            # Creator/Critic/Analyst agents
│   ├── memory.py            # Working memory
│   ├── mcp_core.py          # Orchestration engine
│   └── cli.py               # CLI commands
├── scripts/
├── tests/
├── setup.py
├── pyproject.toml
├── install.sh
└── README.md

CLI Commands

mcp setup              Interactively configure API key
mcp process "task"    Run a task through the cognitive pipeline
mcp sessions          List recent sessions
mcp session <id>      View full session details
mcp status            Check configuration

Hermes Integration

Connect mcp-brain as a native tool server inside Hermes (your AI agent framework). Once connected, Hermes can delegate complex reasoning tasks to the multi-agent pipeline.

Requirements

  • Hermes gateway installed (hermes setup)
  • mcp-brain installed (pip install mcp-brain)

Setup

Step 1: Add to your Hermes config at ~/.hermes/config.yaml:

mcp_servers:
  mcp-brain:
    command: "/home/YOUR_USERNAME/.local/bin/mcp-brain-server"

Find your username with whoami and substitute the path accordingly.

Step 2: Restart the Hermes gateway:

systemctl --user restart hermes-gateway

Step 3: Verify:

hermes status

You should see mcp_mcp_brain_process_task listed as an available tool.

Usage

Once connected, just ask Hermes to think through something complex — it will automatically use the multi-agent pipeline when appropriate:

You: "Explain why volatility clustering occurs in financial markets"
Hermes → mcp-brain Creator/Critic/Analyst pipeline → detailed answer

No cloud hosting, no separate processes to manage. Hermes starts the server on demand.

Privacy

  • All API calls go directly from your machine to MiniMax
  • No intermediary servers
  • Session logs stored locally in ~/.mcp/logs/
  • Your API key stored in ~/.mcp/config.json (keep this file private)

MCP Server · Populars

MCP Server · New

    punkpeye

    FastMCP

    A TypeScript framework for building MCP servers.

    Community punkpeye
    can4hou6joeng4

    boss-agent-cli

    AI-agent-first CLI for BOSS 直聘 — 职位搜索、福利筛选、招聘者工作流、MCP 工具与 AI 简历优化

    Community can4hou6joeng4
    clidey

    WhoDB

    A lightweight next-gen data explorer - Postgres, MySQL, SQLite, MongoDB, Redis, MariaDB, Elastic Search, and Clickhouse with Chat interface

    Community clidey
    Battam1111

    Myco

    Self-evolving cognitive organism for AI agents — eternal devouring, eternal evolution.

    Community Battam1111
    MLS-Tech-Inc

    Shortlist MCP Server

    MCP server for Shortlist — search, queue, and auto-apply to jobs from Claude Code

    Community MLS-Tech-Inc