ModelsAtlas
Explore
Atlas / MCP servers / yuchen20 / Memory-Plus

Memory-PlusSAFE

mcp/yuchen20/memory-plus
MCP server by yuchen20 · agent · hackathon · mcp · Audited 2026-10-08
⚑ Report / re-scanSource ↗

🧠 Memory-Plus is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually reme

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
3 2r · 1w · 0d
Transport
—
License
Apache-2.0
Stars
56
01

Overview

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

[](./LICENSE) [](https://pypi.org/project/memory-plus/) [](https://pepy.tech/projects/memory-plus)

A lightweight, local Retrieval-Augmented Generation (RAG) memory store for MCP agents. Memory-Plus lets your agent record, retrieve, update, and visualize persistent "memories"—notes, ideas, and session context—across runs.

🏆 First Place at the Infosys Cambridge AI Centre Hackathon!

Key Features

  • Record Memories:Save user data, ideas, and important context.
  • Retrieve Memories:Search by keywords or topics over past entries.
  • Recent Memories:Fetch the last N items quickly.
  • Update Memories:Append or modify existing entries seamlessly.
  • Visualize Memories:Interactive graph clusters revealing relationships.
  • File Import (since v0.1.2):Ingest documents directly into memory.
  • Delete Memories (since v0.1.2):Remove unwanted entries.
  • Memory for Memories (since v0.1.4):Now we use resources to teach your AI exactly when (and when not) to recall past interactions.
  • Memory Versioning (since v0.1.4):When memories are updated, we keep the old versions to provide a full history.

Installation

1. Prerequisites

Google API Key Obtain from Google AI Studio and set as GOOGLE_API_KEY in your environment.

Note that we will only use the Gemini Embedding API with this API key, so it is **En
Read from source at commit 568f545809cfOBSERVED · 2026-10-08
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. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add memory-plus --env GOOGLE_API_KEY=${GOOGLE_API_KEY} -- uvx memory-plus
claude-desktop
{
  "mcpServers": {
    "memory-plus": {
      "command": "uvx",
      "args": [
        "memory-plus"
      ],
      "env": {
        "GOOGLE_API_KEY": "${GOOGLE_API_KEY}"
      }
    }
  }
}
03

Exposed tools (3)

2 read · 1 write · 0 destructive.

ToolRiskDescription
recentread
set_whether_to_annonimizewrite
visualizeread
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 (4)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
fastmcp, qdrant-client, langchain, google-genai, numpy, pandas, plotly, scikit-learn
Why it matters. 12 requirement(s) not pinned with ==
Fix. pin exact versions
INFOInventory / provenance · inv.oversize · CWE-1104
imgs/memory_server_banner.png
imgs/memory_server_banner.png
Why it matters. 1411797 bytes not read
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:70
curl -LsSf https://astral.sh/uv/install.sh | sh
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
Readme.zh.md:66
curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 568f545809cffull audit observations/trust-audit/mcp-server/yuchen20__memory-plus.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
2026-10-08568f545809cfSAFEB89first audit
06

Questions

What is the Memory-Plus MCP server?

🧠 Memory-Plus is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually reme

What tools does Memory-Plus expose?

3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Memory-Plus 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 Memory-Plus need?

It reads GOOGLE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How current is this page?

The grade is for one exact copy of the source (568f545809cf), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement