mcpbeat Sign in

Memory Industry MCP Server

local only

Memory Industry runs on your own machine — the client starts it, so there is no endpoint to ping. 612 installs a week from pypi. Last commit 28 Oct 2026.

MemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.

Installs per day peak 140 · avg 17 · +979% w/w
a month agotoday
612
Installs / week
npm · memory-industry
30
Stars
1 open issue
28 Oct 2026
Last commit
5 releases in 90 days
Apache-2.0
License
Rust

What the code does

We read the source, 4 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.

Package points at a different repository leandropg19/memorys
пакет cuba-memorys ссылается на leandropg19/cuba-memorys
Runs an external command npm/bin.js:14
    const out = execFileSync(bin, ["--version"], {
Builds a file path from a variable npm/bin.js:10, npm/postinstall.js:31
const localBin = path.join(__dirname, ".bin", binName);
Builds a database query by concatenation rust/src/graph/pagerank.rs:12, rust/src/handlers/puente.rs:429
        SELECT r.from_entity, r.to_entity,
               r.strength / LN(1.0 + COALESCE(deg.degree, 1)) AS dampened_weight
Page executes code built at runtime rust/src/panel/index.html:232
  $("checks").innerHTML = table(["", "Chequeo", "Detalle"], rows);

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 memory-industry -e 'DATABASE_URL=<DATABASE_URL>' -- npx -y memory-industry
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "memory-industry": {
      "command": "npx",
      "args": [
        "-y",
        "memory-industry"
      ],
      "env": {
        "DATABASE_URL": "<DATABASE_URL>"
      }
    }
  }
}
~/.codex/config.toml
[mcp_servers.memory-industry]
command = "npx"
args = ["-y", "memory-industry"]
env = { DATABASE_URL = "<DATABASE_URL>" }
.cursor/mcp.json
{
  "mcpServers": {
    "memory-industry": {
      "command": "npx",
      "args": [
        "-y",
        "memory-industry"
      ],
      "env": {
        "DATABASE_URL": "<DATABASE_URL>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "memory-industry": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "memory-industry"
      ],
      "env": {
        "DATABASE_URL": "<DATABASE_URL>"
      }
    }
  }
}

Put your own value in place of <DATABASE_URL> (PostgreSQL connection URL (e.g. postgresql://user:pass@localhost:5432/brain)). The author’s registry entry marks it as required.

Optional settings from the registry entry, left out of the block above: CUBA_PROJECT_FILTER (Set to 'off' to disable v0.8 project scoping filters (admin/debug only)), CUBA_SYNC_DIR (Directory used by cuba_sync export/import (default ./.memory-industry/, falls back to ./.cuba-memorys/)), CUBA_JUDGE (cuba_juez backend selector: nli | mcp_sampling | claude_cli | heuristic | auto (default auto)), CUBA_JUEZ_CLI (Subprocess CLI used by ClaudeCodeJudge (default 'claude')), CUBA_JUEZ_MODEL (Model name passed to the judge backend (default 'claude-haiku-4-5')), CUBA_REM_RELATION_BATCH (Isolated entities the REM cycle scans for relations per run (default 5, 0 disables)), CUBA_RERANKER_PATH (Directory holding the bge-reranker ONNX model; enables cross-encoder reranking (+93% nDCG on GPU)), CUBA_RERANK_FIXED_SHAPE (Pad reranker batches to a constant 512 tokens. Defaults on for GPU builds, off on CPU).

Alternatives to Memory Industry

same job, measured the same way
Cuba Memorys
by leandropg19

Persistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.

local only
Memory MCP Server
by j0hanz

SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.

66 installs/wk local only
Dense Knowledge
by lucky44k

Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval.

111 installs/wk local only
Memori MCP
by memorilabs

Memori MCP server — persistent AI memory with recall and augmentation tools

35 installs/wk local only
Contextforge MCP
by alfredoizdev

Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.

216 installs/wk local only
Memstack
by isiomac

MCP server for persistent, searchable memory for AI agents.

119 installs/wk local only
Agentos
by officialtanishsharma

Local-first persistent memory MCP server for AI coding agents.

local only
Memanto
by moorcheh-ai

MCP server for Memanto - persistent semantic memory for any MCP-compatible agent

704 installs/wk local only

Memory Industry — questions

Answers built from our own checks of this server.

Why is there no uptime for Memory Industry?
Memory Industry 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 memory-industry was installed 612 times last week.
How do I connect Memory Industry?
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 memory-industry straight from npm; nothing to host, nothing to sign up for.
How many people use Memory Industry?
The npm package memory-industry was installed 612 times in the last week. Week over week that is +979%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Memory Industry open source?
Yes — it is published under the Apache-2.0 licence, written in Rust, 30 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.