mcpbeat Sign in

KEPTA — the memory for AI systems MCP Server

by damiantodorovic Your server? Claim it
local only

KEPTA — the memory for AI systems runs on your own machine — the client starts it, so there is no endpoint to ping. 402 installs a week from npm. Last commit 13 Oct 2026.

Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.

Installs per day peak 994 · avg 237 · -60% w/w
a month agotoday
402
Installs / week
npm · kepta-mcp
2
Stars
0 open issues
13 Oct 2026
Last commit
51 releases in 90 days
BUSL-1.1
License
TypeScript

What the code does

We read the source, 5 d ago · rules 995398eba69f

Capabilities

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.

File ships in the package but is absent from the source [пакет] bin/kepta.js:1
этот файл ставится пользователю, но в репозитории его нет
In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Claims local-only, but the code calls out server.ts:151
  try { liste = fs.readdirSync(ordner); } catch { return { gehalten: 0, entfernt: 0 }; }
Deletes files or strips permissions src/demo-show.ts:205
  if (rest) zeile([`left behind: ${rest}`, FARBEN.rot], [`remove it with: rm -rf ${rest}`, FARBEN.grau]);
const ziel = path.join(zielVerzeichnis, datei);
Runs an external command src/core/schluessel.ts:44
  execFileSync(befehl, argumente, {
Reads files and sends them to the network server.ts:151
  try { liste = fs.readdirSync(ordner); } catch { return { gehalten: 0, entfernt: 0 }; }

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

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.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add kepta -- npx -y kepta-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "kepta": {
      "command": "npx",
      "args": [
        "-y",
        "kepta-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.kepta]
command = "npx"
args = ["-y", "kepta-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "kepta": {
      "command": "npx",
      "args": [
        "-y",
        "kepta-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "kepta": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "kepta-mcp"
      ]
    }
  }
}

Alternatives to KEPTA — the memory for AI systems

same job, measured the same way
FactMem
by gordonkjlee

A local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.

63 installs/wk local only
agentmem
by oxgeneral

Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.

local only
M3 Memory
by skynetcmd

Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.

1 480 installs/wk local only
Memento
by scrypster

Persistent memory for AI tools. Local-first knowledge graph with hybrid search.

local only
M
Mimir — Persistent Memory Engine
by tcconnally

Persistent memory for AI agents. 36+ MCP tools: encryption, decay, hybrid search, knowledge graph.

local only
Fimemory
by futureaiindustries

Local-first shared memory for AI tools. Your files, encrypted at rest by default; budgeted reads.

65 installs/wk local only
Cozo Memory
by tobs-code

Local-first memory system for AI agents with hybrid search and graph reasoning

43 installs/wk local only
Sthayi
by sthayi-ai

Local-first AI memory over MCP. No account; you own the store.

42 installs/wk local only

KEPTA — the memory for AI systems — questions

Answers built from our own checks of this server.

Why is there no uptime for KEPTA — the memory for AI systems?
KEPTA — the memory for AI systems runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package kepta-mcp was installed 402 times last week.
How do I connect KEPTA — the memory for AI systems?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls kepta-mcp straight from npm; nothing to host, nothing to sign up for.
How many people use KEPTA — the memory for AI systems?
The npm package kepta-mcp was installed 402 times in the last week. Week over week that is -60%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is KEPTA — the memory for AI systems open source?
No, and the distinction matters: its licence is declared as BUSL-1.1. That makes it source-available — you can read the code, but the terms are the author's own, not one of the recognised open-source licences. Read them before you build on it.