WatchlistFirst-party MCP

Mem0 MCP

by Mem0

Updated September 11, 2026

Files & Knowledge

MCP100 verdict

Not currently recommended. Current hosted successor is the right identity, but long-term memory add/update/delete operations require stronger hosted-service evidence before Selected.

MCP100 Assessment

Editorial verdict

Current hosted successor is the right identity, but long-term memory add/update/delete operations require stronger hosted-service evidence before Selected.

Reviewed September 11, 2026

Task Fit

Mapped

Local files and knowledge

Trust

Status warning

Editorial trust review has not been completed.

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals unavailable

No independently comparable adoption metric is currently stored.

Best for

Persistent agent memory backed by Mem0 Platform
Users who want a hosted MCP endpoint instead of running the archived local server

Not ideal for

Sensitive memory stores without clear retention/deletion/account controls
Workflows where the AI should never persist user data

Avoid if

You cannot define acceptable memory retention and deletion policy
You do not trust the AI client with add/update/delete memory permissions

Trade-offs

Cloud hosting simplifies setup but introduces a third-party data boundary
Memory writes can create durable effects that outlive the current session

Evidence scope

Evidence

Current source snapshot

Popularity

No MCP-specific repository metric is stored

No MCP-specific package metric is stored

Stars observation date unavailable · Downloads observation date unavailable

Maintenance

Publisher activity observed September 11, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed September 11, 2026

Evidence source 1 ↗GitHub repository ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Transport not recorded

No official setup found

No sufficient client-specific setup evidence has been stored from the publisher or client documentation.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-09-11T00:00:00.000Z

Evidence 1 ↗

Reviewed setup

Type-appropriate, source-backed setup for this mcp server profile.

Transport: Hosted HTTP
Endpoint: https://mcp.mem0.ai/mcp
Verify: Connect with a test account and confirm the current hosted tool surface before using real memories.
Setup notes: Do not use the archived local repository as the active production identity.

Read additional publisher installation details

From the publisher README

Publisher installation details

Original client setup and configuration retained from the publisher documentation.

View original README ↗

Quick Start

Installation

uv pip install mem0-mcp-server

Or with pip:

pip install mem0-mcp-server

Loading optional publisher installation details…

No complete evidence-backed client setup steps are currently stored. Optional publisher documentation may provide additional context below.

Read publisher documentation

Publisher documentation

Publisher README

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original README ↗

[!CAUTION]

This project has been archived

mem0-mcp-server is no longer actively maintained and this repository is now a public archive.

Thank you to the 640+ stargazers, 140+ forkers, and every contributor who helped shape this project. Your support and feedback meant the world to us.

Looking for Mem0 MCP? We now offer an official cloud-hosted MCP server. Check out the docs to get started.

Quick install across all major clients:
npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "claude,claude code,cursor,windsurf,vscode,opencode"

Mem0 MCP Server

mem0-mcp-server wraps the official Mem0 Memory API as a Model Context Protocol (MCP) server so any MCP-compatible client (Claude Desktop, Cursor, custom agents) can add, search, update, and delete long-term memories.

Tools

The server exposes the following tools to your LLM:

Tool	Description
`add_memory`	Save text or conversation history (or explicit message objects) for a user/agent.
`search_memories`	Semantic search across existing memories (filters + limit supported).
`get_memories`	List memories with structured filters and pagination.
`get_memory`	Retrieve one memory by its `memory_id`.
`update_memory`	Overwrite a memory's text once the user confirms the `memory_id`.
`delete_memory`	Delete a single memory by `memory_id`.
`delete_all_memories`	Bulk delete all memories in the confirmed scope (user/agent/app/run).
`delete_entities`	Delete a user/agent/app/run entity (and its memories).

All responses are JSON strings returned directly from the Mem0 API.

Usage Options

There are three ways to use the Mem0 MCP Server:

Python Package - Install and run locally using uvx with any MCP client
Docker - Containerized deployment that creates an /mcp HTTP endpoint
Smithery - Remote hosted service for managed deployments

Client Configuration

Add this configuration to your MCP client:

{
  "mcpServers": {
    "mem0": {
      "command": "uvx",
      "args": ["mem0-mcp-server"],
      "env": {
        "MEM0_API_KEY": "m0-...",
        "MEM0_DEFAULT_USER_ID": "your-handle"
      }
    }
  }
}

Test with the Python Agent

To test the server immediately, use the included Pydantic AI agent:

# Install the package
pip install mem0-mcp-server
# Or with uv
uv pip install mem0-mcp-server

# Set your API keys
export MEM0_API_KEY="m0-..."
export OPENAI_API_KEY="sk-openai-..."

# Clone and test with the agent
git clone https://github.com/mem0ai/mem0-mcp.git
cd mem0-mcp-server
python example/pydantic_ai_repl.py

Using different server configurations:

# Use with Docker container
export MEM0_MCP_CONFIG_PATH=example/docker-config.json
export MEM0_MCP_CONFIG_SERVER=mem0-docker
python example/pydantic_ai_repl.py

# Use with Smithery remote server
export MEM0_MCP_CONFIG_PATH=example/config-smithery.json
export MEM0_MCP_CONFIG_SERVER=mem0-memory-mcp
python example/pydantic_ai_repl.py

What You Can Do

The Mem0 MCP server enables powerful memory capabilities for your AI applications:

Remember that I'm allergic to peanuts and shellfish - Add new health information to memory
Store these trial parameters: 200 participants, double-blind, placebo-controlled study - Save research data
What do you know about my dietary preferences? - Search and retrieve all food-related memories
Update my project status: the mobile app is now 80% complete - Modify existing memory with new info
Delete all memories from 2023, I need a fresh start - Bulk remove outdated memories
Show me everything I've saved about the Phoenix project - List all memories for a specific topic

Configuration

Environment Variables

MEM0_API_KEY (required) – Mem0 platform API key.
MEM0_DEFAULT_USER_ID (optional) – default user_id injected into filters and write requests (defaults to mem0-mcp).
MEM0_ENABLE_GRAPH_DEFAULT (optional) – Enable graph memories by default (defaults to false).
MEM0_MCP_AGENT_MODEL (optional) – default LLM for the bundled agent example (defaults to openai:gpt-4o-mini).

Advanced Setup

Docker Deployment

To run with Docker:

Build the image:
```
docker build -t mem0-mcp-server .
```

Run the container:

docker run --rm -d \
  --name mem0-mcp \
  -e MEM0_API_KEY=m0-... \
  -p 8080:8081 \
  mem0-mcp-server

Monitor the container:

# View logs
docker logs -f mem0-mcp

# Check status
docker ps

Running with Smithery Remote Server

To connect to a Smithery-hosted server:

Install the MCP server (Smithery dependencies are now bundled):
```
pip install mem0-mcp-server
```

Configure MCP client with Smithery:

{
  "mcpServers": {
    "mem0-memory-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@mem0ai/mem0-memory-mcp",
        "--key",
        "your-smithery-key",
        "--profile",
        "your-profile-name"
      ],
      "env": {
        "MEM0_API_KEY": "m0-..."
      }
    }
  }
}

Development Setup

Clone and run from source:

git clone https://github.com/mem0ai/mem0-mcp.git
cd mem0-mcp-server
pip install -e ".[dev]"

# Run locally
mem0-mcp-server

# Or with uv
uv sync
uv run mem0-mcp-server

License

Apache License 2.0

Loading optional publisher documentation…

FAQ

What does Mem0 MCP do?

Current hosted successor is the right identity, but long-term memory add/update/delete operations require stronger hosted-service evidence before Selected.

How does Mem0 MCP authenticate or get access?

Requires a Mem0 Platform account/API key for the hosted MCP setup.

What permissions does Mem0 MCP have?

Tools can add, search, retrieve, update, and delete long-term memories within the Mem0 account scope.

What are the main risks of using Mem0 MCP?

High for sensitive contexts. Persistent memory can store private content and delete/update operations are durable; tenant, retention, audit, and revocation controls need periodic review.

What does Mem0 MCP cost to use?

Mem0 Platform pricing/limits apply.

Is this an official MCP?

Mem0 is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

[!CAUTION]

This project has been archived

mem0-mcp-server is no longer actively maintained and this repository is now a public archive.

Thank you to the 640+ stargazers, 140+ forkers, and every contributor who helped shape this project. Your support and feedback meant the world to us.

Looking for Mem0 MCP? We now offer an official cloud-hosted MCP server. Check out the docs to get started.

Quick install across all major clients:
npx mcp-add \
  --name mem0-mcp \
  --type http \
  --url "https://mcp.mem0.ai/mcp" \
  --clients "claude,claude code,cursor,windsurf,vscode,opencode"

Mem0 MCP Server

Tools

The server exposes the following tools to your LLM:

Tool	Description
`add_memory`	Save text or conversation history (or explicit message objects) for a user/agent.
`search_memories`	Semantic search across existing memories (filters + limit supported).
`get_memories`	List memories with structured filters and pagination.
`get_memory`	Retrieve one memory by its `memory_id`.
`update_memory`	Overwrite a memory's text once the user confirms the `memory_id`.
`delete_memory`	Delete a single memory by `memory_id`.
`delete_all_memories`	Bulk delete all memories in the confirmed scope (user/agent/app/run).
`delete_entities`	Delete a user/agent/app/run entity (and its memories).

All responses are JSON strings returned directly from the Mem0 API.

Usage Options

There are three ways to use the Mem0 MCP Server:

Python Package - Install and run locally using uvx with any MCP client
Docker - Containerized deployment that creates an /mcp HTTP endpoint
Smithery - Remote hosted service for managed deployments

Client Configuration

Add this configuration to your MCP client:

{
  "mcpServers": {
    "mem0": {
      "command": "uvx",
      "args": ["mem0-mcp-server"],
      "env": {
        "MEM0_API_KEY": "m0-...",
        "MEM0_DEFAULT_USER_ID": "your-handle"
      }
    }
  }
}

Test with the Python Agent

To test the server immediately, use the included Pydantic AI agent:

# Install the package
pip install mem0-mcp-server
# Or with uv
uv pip install mem0-mcp-server

# Set your API keys
export MEM0_API_KEY="m0-..."
export OPENAI_API_KEY="sk-openai-..."

# Clone and test with the agent
git clone https://github.com/mem0ai/mem0-mcp.git
cd mem0-mcp-server
python example/pydantic_ai_repl.py

Using different server configurations:

# Use with Docker container
export MEM0_MCP_CONFIG_PATH=example/docker-config.json
export MEM0_MCP_CONFIG_SERVER=mem0-docker
python example/pydantic_ai_repl.py

# Use with Smithery remote server
export MEM0_MCP_CONFIG_PATH=example/config-smithery.json
export MEM0_MCP_CONFIG_SERVER=mem0-memory-mcp
python example/pydantic_ai_repl.py

What You Can Do

The Mem0 MCP server enables powerful memory capabilities for your AI applications:

Remember that I'm allergic to peanuts and shellfish - Add new health information to memory
Store these trial parameters: 200 participants, double-blind, placebo-controlled study - Save research data
What do you know about my dietary preferences? - Search and retrieve all food-related memories
Update my project status: the mobile app is now 80% complete - Modify existing memory with new info
Delete all memories from 2023, I need a fresh start - Bulk remove outdated memories
Show me everything I've saved about the Phoenix project - List all memories for a specific topic

Configuration

Environment Variables

MEM0_API_KEY (required) – Mem0 platform API key.
MEM0_DEFAULT_USER_ID (optional) – default user_id injected into filters and write requests (defaults to mem0-mcp).
MEM0_ENABLE_GRAPH_DEFAULT (optional) – Enable graph memories by default (defaults to false).
MEM0_MCP_AGENT_MODEL (optional) – default LLM for the bundled agent example (defaults to openai:gpt-4o-mini).

Advanced Setup

Docker Deployment

To run with Docker:

Build the image:
```
docker build -t mem0-mcp-server .
```

Run the container:

docker run --rm -d \
  --name mem0-mcp \
  -e MEM0_API_KEY=m0-... \
  -p 8080:8081 \
  mem0-mcp-server

Monitor the container:

# View logs
docker logs -f mem0-mcp

# Check status
docker ps

Running with Smithery Remote Server

To connect to a Smithery-hosted server:

Install the MCP server (Smithery dependencies are now bundled):
```
pip install mem0-mcp-server
```

Configure MCP client with Smithery:

{
  "mcpServers": {
    "mem0-memory-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@mem0ai/mem0-memory-mcp",
        "--key",
        "your-smithery-key",
        "--profile",
        "your-profile-name"
      ],
      "env": {
        "MEM0_API_KEY": "m0-..."
      }
    }
  }
}

Development Setup

Clone and run from source:

git clone https://github.com/mem0ai/mem0-mcp.git
cd mem0-mcp-server
pip install -e ".[dev]"

# Run locally
mem0-mcp-server

# Or with uv
uv sync
uv run mem0-mcp-server

License

Apache License 2.0

Current hosted successor is the right identity, but long-term memory add/update/delete operations require stronger hosted-service evidence before Selected.

Best for

Not ideal for

Avoid if

Trade-offs

Evidence

Popularity

Maintenance

Trust review

Install & Agents

Claude Code

Reviewed setup

Publisher installation details

Quick Start

Installation

What it does

Representative uses

Important limits

Context Footprint

Access & risk

Other options

Codebase Memory

MCPVault for Obsidian

Excel MCP Server

Publisher README

This project has been archived

Mem0 MCP Server

Tools

Usage Options

Client Configuration

Test with the Python Agent

What You Can Do

Configuration

Environment Variables

Advanced Setup

Docker Deployment

Running with Smithery Remote Server

Development Setup

License

FAQ

Publisher installation details

Quick Start

Installation

Publisher README

This project has been archived

Mem0 MCP Server

Tools

Usage Options

Client Configuration

Test with the Python Agent

What You Can Do

Configuration

Environment Variables

Advanced Setup

Docker Deployment

Running with Smithery Remote Server

Development Setup

License