Memory Pulse runs on your own machine — the client starts it, so there is no endpoint to ping. 165 installs a week from npm. Last commit 23 Oct 2026.
Give any agent self-improving memory you can trust in production. Built-in memory security.
We read the source, 7 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.
try { const p = spawn(cmd, args, { stdio: "ignore", detached: true }); p.on("error", () => {}); p.unref(); } catch { /* the link is printed anyway */ }
import { existsSync, mkdirSync, readFileSync, appendFileSync, writeFileSync, realpathSync, readdirSync, statSync, renameSync, unlinkSync, openSync, closeSync, writeSync, truncateSync, linkSync, copyFileSync, rmSync } from "node:fs";
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 memory-pulse -- npx -y memory-pulse
{
"mcpServers": {
"memory-pulse": {
"command": "npx",
"args": [
"-y",
"memory-pulse"
]
}
}
}
[mcp_servers.memory-pulse]
command = "npx"
args = ["-y", "memory-pulse"]
{
"mcpServers": {
"memory-pulse": {
"command": "npx",
"args": [
"-y",
"memory-pulse"
]
}
}
}
{
"servers": {
"memory-pulse": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"memory-pulse"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MEMORY_PULSE_KEY (License key (optional; free tier without one)), MEMORY_PULSE_LEDGER (Ledger file path (default ./.memory-pulse/events.jsonl)), MEMORY_PULSE_BOARD (Shared agent message board file; set it to add board_post and board_read).
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
Ask your security cameras anything and set up alert rules in a sentence. Built into Agent DVR.
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
Security scanning and trust verification for AI agent tools.
Agent security pre-checks: prompt-injection scan, MCP tool-poisoning scan, x402 endpoint check.
Improve security writing, score it against rubrics, plan IR, CTI, vuln, and product strategy.
Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.
Trooth is an infrastructure and cybersecurity company providing Machine-Readable Trust.
Answers built from our own checks of this server.