Agent Magnet runs on your own machine — the client starts it, so there is no endpoint to ping. 298 installs a week from pypi. Last commit 6 Sep 2026.
Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.
What the code does
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
def eval(self, script: str, numkeys: int, *keys_and_args: str) -> list:
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agent-magnet -e 'MAGNET_USER_ID=<MAGNET_USER_ID>' -- uvx agent-magnet{
"mcpServers": {
"agent-magnet": {
"command": "uvx",
"args": [
"agent-magnet"
],
"env": {
"MAGNET_USER_ID": "<MAGNET_USER_ID>"
}
}
}
}[mcp_servers.agent-magnet]
command = "uvx"
args = ["agent-magnet"]
env = { MAGNET_USER_ID = "<MAGNET_USER_ID>" }{
"mcpServers": {
"agent-magnet": {
"command": "uvx",
"args": [
"agent-magnet"
],
"env": {
"MAGNET_USER_ID": "<MAGNET_USER_ID>"
}
}
}
}{
"servers": {
"agent-magnet": {
"type": "stdio",
"command": "uvx",
"args": [
"agent-magnet"
],
"env": {
"MAGNET_USER_ID": "<MAGNET_USER_ID>"
}
}
}
}Put your own value in place of
<MAGNET_USER_ID> (Your identifier used as the memory key across all tools).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
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')).
Alternatives to Agent Magnet
same job, measured the same wayLint, measure, and sync AI context files across Cursor, Claude Code, Copilot.
Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.
Private memory for AI agents: save and recall facts across Claude Code, Codex, Cursor and ChatGPT.
ContextStream MCP server for code context, memory, search, and AI tools.
Wontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.
Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.
Persistent cross-project memory for Cursor and Claude Code using local semantic search.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Agent Magnet — questions
Answers built from our own checks of this server.