Memtrust runs on your own machine — the client starts it, so there is no endpoint to ping. 240 installs a week from pypi. Last commit 25 Aug 2026.
Independent, reproducible benchmark harness for agent-memory backends.
We read the source, 11 h ago · rules 3dff92dd89df
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(
result = subprocess.run(command, capture_output=True, text=True, timeout=600)
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 memtrust -- uvx memtrust-cli
{
"mcpServers": {
"memtrust": {
"args": [
"memtrust-cli"
],
"command": "uvx"
}
}
}
[mcp_servers.memtrust]
command = "uvx"
args = ["memtrust-cli"]
{
"mcpServers": {
"memtrust": {
"args": [
"memtrust-cli"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"memtrust": {
"args": [
"memtrust-cli"
],
"command": "uvx"
}
}
}
Benchmark, memory, Big O analysis for AI agents
Local-first, cross-harness memory for AI coding agents.
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Durable local-first MCP relay for independent coding agents.
Persistent memory for AI agents with OAuth-backed hosted MCP access.
One shared, durable memory for your AI coding agents — local-first, zero-dependency.
A lightweight, Git-backed permanent memory for AI agents.
Persistent graph-backed conversational memory for AI agents.
Answers built from our own checks of this server.