PADAM · NOCTURNE memory runs on your own machine — the client starts it, so there is no endpoint to ping. 6 994 installs a week from pypi. Last commit 19 Nov 2026.
Local memory for AI agents: masks secrets, holds injected orders for review, forgets one record
We read the source, 10 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.
этот файл ставится пользователю, но в репозитории его нет
p = subprocess.Popen([python, "-m", "padam.mcp_server"], stdin=subprocess.PIPE, stdout=subprocess.PIPE,
const r = spawnSync(probe, [cmd], { stdio: "ignore" });
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 padam-nocturne -- uvx padam-nocturne
{
"mcpServers": {
"padam-nocturne": {
"command": "uvx",
"args": [
"padam-nocturne"
]
}
}
}
[mcp_servers.padam-nocturne]
command = "uvx"
args = ["padam-nocturne"]
{
"mcpServers": {
"padam-nocturne": {
"command": "uvx",
"args": [
"padam-nocturne"
]
}
}
}
{
"servers": {
"padam-nocturne": {
"type": "stdio",
"command": "uvx",
"args": [
"padam-nocturne"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
PADAM_DB (Path to the SQLite memory file. Default: ~/.padam/memory.db), OLLAMA_URL (Local Ollama address for embeddings. Without it a built-in method is used), PADAM_STRICT (1 turns on every guard at once: each agent write waits for the owner's review, and switches that weaken protection are ignored).
Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
Agent-safe secrets (local encrypted vault or Vaultwarden): injected into commands, masked in output
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
One firewall and password manager for all your AI coding agents' MCP servers and secrets.
IaC, CI and dependency security review for coding agents: local scan CLI plus hosted OAuth MCP.
Safety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
Answers built from our own checks of this server.