Agent Memory MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 191 installs a week from npm. Last commit 1 Nov 2026.
Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.
We read the source, 23 h 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.
const result = spawnSync(editor, [fp], { stdio: "inherit" });
readdirSync,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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-memory-mcp -- npx -y @xultrax-web/agent-memory-mcp
{
"mcpServers": {
"agent-memory-mcp": {
"command": "npx",
"args": [
"-y",
"@xultrax-web/agent-memory-mcp"
]
}
}
}
[mcp_servers.agent-memory-mcp]
command = "npx"
args = ["-y", "@xultrax-web/agent-memory-mcp"]
{
"mcpServers": {
"agent-memory-mcp": {
"command": "npx",
"args": [
"-y",
"@xultrax-web/agent-memory-mcp"
]
}
}
}
{
"servers": {
"agent-memory-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@xultrax-web/agent-memory-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
AGENT_MEMORY_DIR (Absolute path to a custom memory storage directory. Overrides the default per-project location), AGENT_MEMORY_SCOPE (Set to 'global' to store memories in ~/.agent-memory/ instead of the per-project default ./.agent-memory/), AGENT_MEMORY_LOG (Log level: debug | info | warn | error. Defaults to info. Logs go to stderr (won't pollute MCP stdio)).
Memory for AI coding agents — markdown in your own git, not a vendor database. Apache-2.0.
Markdown-first Notion for AI agents -- pages, databases, blocks, and comments in one call.
The engine of your second brain: Markdown notes as database tables, for you and your agents.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL.
Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.
Notion for AI agents — search, read pages/blocks, query databases, create pages.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
Answers built from our own checks of this server.