Mem0 for Project Management MCP server

Bridge to the mem0 cloud service, providing memory capabilities.
Back to servers
Setup instructions
Provider
Kunihiro Setogawa
Release date
Mar 26, 2025
Language
Python
Stats
6 stars

The mem0 MCP Server connects MCP Host applications with the mem0 cloud service, providing structured project memory management and semantic search capabilities for project-related information.

Installation

Prerequisites

You need to have pipx installed on your system to run the mem0 MCP Server. If you don't have pipx installed, you can install it using pip:

pip install pipx

Setting Up Your Environment

Before using the mem0 MCP Server, you need a mem0 API key. This key should be set as an environment variable:

export MEM0_API_KEY="your_mem0_api_key_here"

Configuration

MCP Host Configuration

When configuring your MCP Host to use the mem0 MCP Server, you must specify the log output mode and, if enabled, the absolute log file path.

Configuration with Logging Disabled

"mem0": {
  "command": "pipx",
  "args": ["run", "mem0-mcp-for-pm", "--log=off"],
  "env": {
    "MEM0_API_KEY": "{apikey}"
  }
}

Configuration with Logging Enabled

"mem0": {
  "command": "pipx",
  "args": ["run", "mem0-mcp-for-pm", "--log=on", "--logfile=/workspace/logs/mem0-mcp-server.log"],
  "env": {
    "MEM0_API_KEY": "{apikey}"
  }
}

Version Specification

If you're experiencing issues due to caching of older versions, specify the exact version:

"mem0": {
  "command": "pipx",
  "args": ["run", "mem0-mcp-for-pm==0.3.2", "--log=off"],
  "env": {
    "MEM0_API_KEY": "{apikey}"
  }
}

Using the MCP Server Tools

The mem0 MCP Server provides several tools for managing project memories:

Adding Project Memory

Use the add_project_memory tool to store new project information. All project memory entries must be in TOML format.

Example TOML for project status:

category = "Project Status"
project = "project-name"
timestamp = "2025-04-29T16:00:00+09:00"
name = "Project Name"
purpose = "Project Purpose"
version = "1.2.0"
phase = "development"
completionLevel = 0.65
milestones = ["Planning", "Development"]
currentFocus = ["Implementing Feature X", "Optimizing Component Y"]

[metadata]
type = "status"
priority = "high"
tags = ["backend", "release"]

Retrieving Project Memories

To get all project memories:

get_all_project_memories

Searching Project Memories

To search for specific memories:

search_project_memories

Updating Project Memory

To update existing project information:

update_project_memory

Deleting Project Memories

To delete a specific project memory:

delete_project_memory

To delete all project memories:

delete_all_project_memories

Best Practices for TOML Formatting

Using Run ID for Context Management

Use the run_id parameter to logically group related entries:

run_id = "project:member-system:feature:authentication"

Effective Metadata Usage

Always add a [metadata] TOML table to enhance search and filtering:

[metadata]
type = "task"
priority = "high"
tags = ["frontend"]

Template Examples

Task Management Example

category = "Task Management"
project = "project-name"
timestamp = "2025-04-29T16:00:00+09:00"

[[tasks]]
description = "Implement Feature X"
status = "in-progress"
deadline = "2025-05-15"
assignee = "Team A"
dependencies = ["Component Y"]

[metadata]
type = "task"
priority = "high"
tags = ["frontend", "authentication"]

Meeting Summary Example

category = "Meeting Summary"
project = "project-name"
timestamp = "2025-04-29T16:00:00+09:00"
title = "Weekly Progress Meeting"
date = "2025-03-23"
attendees = ["Sato", "Suzuki", "Tanaka"]
topics = ["Progress Report", "Risk Management", "Next Week's Plan"]
decisions = ["Approve additional resource allocation", "Delay release date by one week"]

[[actionItems]]
description = "Procedure for adding resources"
assignee = "Sato"
dueDate = "2025-03-25"

[metadata]
type = "meeting"
tags = ["weekly", "progress"]

Information Lifecycle Management

Use these parameters to manage the lifecycle of your information:

immutable = true  # Prevents updates
expiration_date = "2025-06-30"  # Sets expiry date

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mem0" '{"command":"pipx","args":["run","mem0-mcp-for-pm","--log=off"],"env":{"MEM0_API_KEY":"{apikey}"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mem0": {
            "command": "pipx",
            "args": [
                "run",
                "mem0-mcp-for-pm",
                "--log=off"
            ],
            "env": {
                "MEM0_API_KEY": "{apikey}"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

{
    "mcpServers": {
        "mem0": {
            "command": "pipx",
            "args": [
                "run",
                "mem0-mcp-for-pm",
                "--log=off"
            ],
            "env": {
                "MEM0_API_KEY": "{apikey}"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later