MCP.Market

Agent Magnet MCP server

by helinakdogan·io.github.helinakdogan/agent-magnet·v0.1.11·14 stars
No reviews yet

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

A85/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

14 stars86 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Magnet yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Magnet tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_signal

    Record a behavioral signal from user interaction

  • end_session

    Summarize and save current session to memory

  • get_cold_start

    Get cold start profile for a new user

  • get_profile

    Get the learned memory profile for a user

  • inject_memory

    Get memory injection string for system prompt

  • save_session

    Manually save current session to memory (use when the Stop hook is unavailable)

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

1 medium
  • Code scan18 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 21 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    agent_magnet-0.1.11/magnet/buffer.py: …edis: results = self._redis.eval(_ATOMIC_FLUSH_SCRIPT, 1, key) …
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Magnet compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 73% of 4,460 AI and agents servers
Tools
6
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
14
more than 86% of 2,711 AI and agents servers
Downloads a week
86
more than 60% of 1,538 AI and agents servers with a package

What its tools let an agent do: 4 read · 2 create

Install Agent Magnet in Claude Code, Cursor or VS Code

claude mcp add agent-magnet -- uvx agent-magnet
Add to Cursor

What the publisher says

From the Agent Magnet repository's README, as published. We do not edit it. Read it on GitHub

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.

Manual MCP config (Codex, or any other MCP client)

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

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

Nothing above is checked by us. What we check is on the safety report.

Agent Magnet: common questions

Is Agent Magnet MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Agent Magnet safety report
How do I install Agent Magnet?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Magnet need an API key?
No secret keys are declared. It reads 5 settings from the environment.
Is Agent Magnet maintained?
The last commit was 60 days ago (2026-09-05). The latest release is v0.1.11.
What can I use instead of Agent Magnet?
Servers from other publishers that do the same job: Mnemoverse Memory MCP server, Agent Recall MCP server and agent-device MCP server.
How does Agent Magnet compare with other AI and agents MCP servers?
safety score 85/100 (higher than 73% of 4,460 AI and agents servers); tools 6 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Magnet

Same job from other publishers: the closest match first, then the best rated.

  • Mnemoverse Memory
    Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
    A
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A
  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • LLM Sandbox
    Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B