Memtether runs on your own machine — the client starts it, so there is no endpoint to ping. 3 567 installs a week from pypi. Last commit 8 Nov 2026.
Cross-client AI memory hub: agents share one SQLite memory.db via file-level pointers.
We read the source, 7 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.
yaml.load(text, Loader=_Loader)
mod = __import__(os.path.splitext(os.path.basename(cred_path))[0])
dst_dir = os.path.join(BACKUP_ROOT, stamp, client_id)
r = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout, env=env, cwd=ROOT)
box.innerHTML=top.map(({f},i)=>`
_e = dict(os.environ); _e['PYTHONIOENCODING']='utf-8'
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 memtether -- uvx memtether
{
"mcpServers": {
"memtether": {
"command": "uvx",
"args": [
"memtether"
]
}
}
}
[mcp_servers.memtether]
command = "uvx"
args = ["memtether"]
{
"mcpServers": {
"memtether": {
"command": "uvx",
"args": [
"memtether"
]
}
}
}
{
"servers": {
"memtether": {
"type": "stdio",
"command": "uvx",
"args": [
"memtether"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MEM_DB (Optional: override default memory database path), MEM_DEFAULT_SOURCE (Optional: override default source attribution for memory writes).
Local-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.
Cross-session memory for AI coding agents via six tools; local-first SQLite store.
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Persistent memory for AI coding agents: one Rust binary, one local SQLite database.
Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.
Answers built from our own checks of this server.