Atlas / MCP servers / baryhuang / OpenMemory

OpenMemorySAFE

mcp/baryhuang/openmemory

Simple standalone MCP server giving Claude the ability to remember your conversations and learn from them over time.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
3 3r · 0w · 0d
Transport
stdio
License
MIT
Stars
71
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.npmjs.com/package/@peakmojo/mcp-openmemory) [](https://opensource.org/licenses/MIT) [](https://modelcontextprotocol.io/)

Gives Claude the ability to remember your conversations and learn from them over time.

https://github.com/user-attachments/assets/aef82b8e-3793-4ebd-b993-ddaef14d52d1

Features

  • Memory Storage: Save and recall conversation messages
  • Memory Abstracts: Maintain summarized memory context across conversations
  • Recent History: Access recent conversations within configurable time windows
  • Local Database: Uses SQLite for persistent storage without external dependencies

⚠️ Important

You must configure `MEMORY_DB_PATH` to a persistent location to avoid losing your conversation history when Claude Desktop closes. If not configured, the database defaults to ./memory.sqlite in a temporary location that may be cleared when the application restarts.

Configuration

Prerequisites

  • Node.js: Required to run the MCP server. Verify installation with:
node --version

If not installed, download from nodejs.org

Claude Desktop Integration

Configuration File Location

The Claude Desktop configuration file is located at:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

To access: Open Claude Desktop → Claude menu → Settings → Developer → Edit Config

macOS/Linux

Run directly using npm

{
"mcpServers": {
"mcp-openmemory": {
"command": "npx",
"args": [
"@peakmojo/mcp-openme
Read from source at commit b2d43dd8db26OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add mcp-openmemory -- npx -y @peakmojo/[email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-openmemory": {
      "command": "npx",
      "args": [
        "-y",
        "@peakmojo/[email protected]"
      ]
    }
  }
}
03

Exposed tools (3)

3 read · 0 write · 0 destructive.

ToolRiskDescription
agent_namereadName of the agent
days_backreadNumber of days to look back (default: 7)
memory_summaryreadGenerate a summary of stored memories for an agent
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (1)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, node-ssh, sql.js, zod
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha b2d43dd8db26full audit observations/trust-audit/mcp-server/baryhuang__openmemory.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07b2d43dd8db26SAFEB89first audit
06

Questions

What is the OpenMemory MCP server?

Simple standalone MCP server giving Claude the ability to remember your conversations and learn from them over time.

What tools does OpenMemory expose?

3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is OpenMemory safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does OpenMemory need?

No credential environment variables were found in its source, so it appears to need none.

How does OpenMemory run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @peakmojo/mcp-openmemory at 0.1.4.

How current is this page?

The grade is for one exact copy of the source (b2d43dd8db26), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement