MCP Server

Active

MIT

io.github.helinakdogan/agent-magnet MCP Server

io.github.helinakdogan/agent-magnet

Behavioral memory layer that learns your preferences and context across Claude, Cursor, and Codex.

What is the io.github.helinakdogan/agent-magnet MCP server?

Agent Magnet is an MCP server that provides a persistent behavioral memory layer for AI tools. It automatically learns your project decisions, conventions, preferences, and context across Claude, Cursor, and Codex sessions, eliminating the need to re-explain context in each new conversation. Memory is stored locally by default and can be shared across teams with a paid key.

Agent Magnet solves the problem of AI tools forgetting your project context between sessions. It automatically captures and organizes decisions, conventions, failed attempts, goals, and preferences as you work, then makes that memory available across Claude, Cursor, and Codex. You can mark items as done or forget them to keep memory focused and relevant.

How to install io.github.helinakdogan/agent-magnet

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

MAGNET_USER_ID
required
Your identifier used as the memory key across all tools
MAGNET_OPENAI_KEY
OpenAI API key for the reflector and classifier models
MAGNET_LOCAL_MODE
Set to 1 to use local SQLite storage — no Redis or external services needed
MAGNET_REDIS_URL
Redis connection URL for persistent shared storage (overrides local mode)
MAGNET_PROJECT_ID
Namespace for memory isolation across projects (defaults to 'default')

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-magnet": {
      "command": "uvx",
      "args": [
        "agent-magnet"
      ],
      "env": {
        "MAGNET_USER_ID": "<YOUR_MAGNET_USER_ID>",
        "MAGNET_OPENAI_KEY": "<YOUR_MAGNET_OPENAI_KEY>",
        "MAGNET_LOCAL_MODE": "<YOUR_MAGNET_LOCAL_MODE>",
        "MAGNET_REDIS_URL": "<YOUR_MAGNET_REDIS_URL>",
        "MAGNET_PROJECT_ID": "<YOUR_MAGNET_PROJECT_ID>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

Memory storage and retrieval — Automatically learns and stores project decisions, conventions, watch-outs, failed attempts, goals, and preferences
Cross-tool memory sharing — Shares one unified memory across Claude, Cursor, and Codex
Memory management — Allows forgetting or marking items as done to prevent memory from accumulating unnecessarily
Team memory — Enables shared memory across team members with a paid Agent Magnet key

Use cases

Maintain consistent project context across multiple Claude, Cursor, and Codex sessions without re-explaining conventions
Share architectural decisions and project conventions automatically with team members
Track failed attempts and learnings to avoid repeating mistakes in future work
Keep a persistent record of project goals and preferences that inform AI suggestions
Reduce context window usage by having the AI reference stored memory instead of re-explaining everything

io.github.helinakdogan/agent-magnet MCP server FAQ

What is Agent Magnet?

Agent Magnet is a behavioral memory layer that automatically learns your project context, decisions, and preferences, then shares that memory across Claude, Cursor, and Codex so you don't have to re-explain things in each session.

Is Agent Magnet free?

Yes, the core local memory functionality is free and MIT licensed. Team memory sharing requires a paid Agent Magnet key from agentmagnet.app.

How do I install it in Claude or Cursor?

Run `pip install agent-magnet` then `agent-magnet init`. The tool automatically detects and configures Claude Desktop and Cursor for you.

Does it require any external services?

No, Agent Magnet stores memory locally by default with no Redis, databases, or API keys required. Team memory sharing is optional and requires a paid key.

What types of information does it remember?

It learns decisions, conventions, watch-outs, failed attempts, goals, preferences, and actions taken — automatically categorized and organized.

Can I control what gets remembered?

Yes, you can mark items as done or explicitly forget things to prevent memory from just piling up.

README (reference)

Source of truth, from the repository.

Your AI forgets your project every new session. This fixes that.

What it does

Learns automatically as you work — no "remember this" required
Shares one memory across Claude, Cursor, and Codex
Lets you forget or mark things done — memory doesn't just pile up

Quick start

pip install agent-magnet
agent-magnet init

That's the whole install. No Redis, no keys, local by default.

What it remembers

Decisions, conventions, watch-outs, failed attempts, goals, preferences, and actions taken — one memory, sorted automatically.

Team memory

Shared memory for a team — one person's decision becomes everyone's context. Requires a paid Agent Magnet key from agentmagnet.app.

Works everywhere

Claude, Cursor, Codex — same memory, local by default. agent-magnet init detects and configures Claude Code, Claude Desktop, and Cursor for you.

<details> <summary>Manual MCP config (Codex, or any other MCP client)</summary>

{
  "mcpServers": {
    "agent-magnet": {
      "command": "agent-magnet-mcp",
      "env": { "MAGNET_USER_ID": "your_name" }
    }
  }
}

</details>

MIT licensed. Contribute — and a ⭐ if this saved your context window.

Related MCP servers

io.github.heliograph-io/heliograph

Active

Run commands on a machine you cannot SSH into. Air-gapped, bastion-only, change-controlled.

Shell

Apache-2.0

View repository →

io.github.heliosarchitect/wems

Maintained

Real-time natural hazard monitoring: earthquakes, tsunamis, volcanoes, solar weather, air quality

Python

MIT

View repository →

GopherHole Agent Hub

Active

Standards-based A2A hub. One MCP connection to thousands of agents, with shared persistent memory.

TypeScript

MIT

View repository →

io.github.hello532/shop-mcp

Read-only Shopify catalogue and stock for LLM agents. Stdlib only, no dependencies.

View repository →

io.github.helloaigent-dev/helloaigent-publisher

Active

Run a Hello Aigent feed from your agent: create feeds, publish signed updates, read analytics.

JavaScript

MIT

View repository →

io.github.helloaigent-dev/helloaigent-subscriber

Active

Subscribe your agent to Hello Aigent feeds: discover, fetch signed updates, verify, and act.

TypeScript

MIT

View repository →