ModelsAtlas
Explore
Atlas / MCP servers / coleam00 / Mem0

Mem0SAFE

mcp/coleam00/mem0-4
MCP server by coleam00 · Audited 2026-09-28
⚑ Report / re-scanSource ↗

MCP server for long term agent memory with Mem0. Also useful as a template to get you started building your own MCP server with Python!

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
3 2r · 1w · 0d
Transport
—
License
MIT
Stars
684
01

Overview

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

MCP-Mem0: Long-Term Memory for AI Agents

A template implementation of the Model Context Protocol (MCP) server integrated with Mem0 for providing AI agents with persistent memory capabilities.

Use this as a reference point to build your MCP servers yourself, or give this as an example to an AI coding assistant and tell it to follow this example for structure and code correctness!

Overview

This project demonstrates how to build an MCP server that enables AI agents to store, retrieve, and search memories using semantic search. It serves as a practical template for creating your own MCP servers, simply using Mem0 and a practical example.

The implementation follows the best practices laid out by Anthropic for building MCP servers, allowing seamless integration with any MCP-compatible client.

Features

The server provides three essential memory management tools:

  1. `save_memory`: Store any information in long-term memory with semantic indexing
  2. `get_all_memories`: Retrieve all stored memories for comprehensive context
  3. `search_memories`: Find relevant memories using semantic search

Prerequisites

  • Python 3.12+
  • Supabase or any PostgreSQL database (for vector storage of memories)
  • API keys for your chosen LLM provider (OpenAI, OpenRouter, or Ollama)
  • Docker if running the MCP server as a container (recommended)

Installation

Using uv

  1. Install uv if you don't have it:
pip install uv
  1. Clone this repository:
git clone https://github.com/coleam00/mcp-mem0.git
cd mcp-mem0
  1. Install dependencies:
uv pip install -e .
  1. Create a .env file based on .env.example:
cp .env.example .env
  1. Configure your environment variables in the .env file (see Configuration
Read from source at commit 93b5b39fc540OBSERVED · 2026-09-28
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 mem0-mcp --env LLM_API_KEY=${LLM_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} --env OPENROUTER_API_KEY=${OPENROUTER_API_KEY} -- uvx mem0-mcp
claude-desktop
{
  "mcpServers": {
    "mem0-mcp": {
      "command": "uvx",
      "args": [
        "mem0-mcp"
      ],
      "env": {
        "LLM_API_KEY": "${LLM_API_KEY}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}",
        "OPENROUTER_API_KEY": "${OPENROUTER_API_KEY}"
      }
    }
  }
}
03

Exposed tools (3)

2 read · 1 write · 0 destructive.

ToolRiskDescription
get_all_memoriesreadGet all stored memories for the user.
save_memorywriteSave information to your long-term memory.
search_memoriesreadSearch memories using semantic search.
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
pinned
Secrets in source
none-found

Findings (1)

INFOInventory / provenance · inv.oversize · CWE-1104
public/Mem0AndMCP.png
public/Mem0AndMCP.png
Why it matters. 1014044 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-09-28 · audit v0.4.1 · source sha 93b5b39fc540full audit observations/trust-audit/mcp-server/coleam00__mem0-4.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
2026-09-2893b5b39fc540SAFEB89first audit
06

Questions

What is the Mem0 MCP server?

MCP server for long term agent memory with Mem0. Also useful as a template to get you started building your own MCP server with Python!

What tools does Mem0 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 Mem0 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 Mem0 need?

It reads LLM_API_KEY, OPENAI_API_KEY and OPENROUTER_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 (93b5b39fc540), read on 2026-09-28. The repository is watched and re-audited when it changes.

Advertisement