MCP Mem0
Mcp Mem0 provides AI agents with persistent long-term memory capabilities by integrating the Model Context Protocol with the Mem0 memory platform. The server exposes three tools—`save_memory`, `get_all_memories`, and `search_memories`—that enable agents to store information with semantic indexing, retrieve all stored memories, and perform semantic searches across a PostgreSQL database. It solves the problem of AI agents lacking persistent memory between sessions by offering a template implementation that demonstrates MCP server best practices and can be deployed via Python or Docker.
- GitHub stars
- 677
- tools
- 3
- last updated
- Dec 15, 2025
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
save_memoryStore any information in long-term memory with semantic indexing.
Store any information in long-term memory with semantic indexing.
No parameter schema in public metadata yet.
get_all_memoriesRetrieve all stored memories for comprehensive context.
Retrieve all stored memories for comprehensive context.
No parameter schema in public metadata yet.
search_memoriesFind relevant memories using semantic search.
Find relevant memories using semantic search.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
MCP-Mem0: Long-Term Memory for AI Agents
Mem0 and MCP Integration
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:
Details
- Repository
- github.com/coleam00/mcp-mem0
- Categories
- AI & LLM Tools, Search & Web Crawling
More from coleam00
Related AI & LLM Tools MCP servers
View all
Mem0mem0ai/mem0-mcpProvides memory management via MCP for adding, searching, updating, and deleting long-term memories across users, agents, and runs.651stars
SEO Skilliannuttall/seoSearch Console, Google Analytics and keyword data for your AI agent.622stars
LINE Botline/line-bot-mcp-serverMCP server that connects an AI agent to LINE Official Account for messaging, rich menus, and profile access.583stars
Misakanetikalus1988/misakanetFailure-memory layer for coding agents: search evidence-rated failure lessons by error text.561stars
Vibe Check Mcp Serverpv-bhat/vibe-check-mcp-serverMetacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety488stars
Clawdcursoramrdab/clawdcursorSafe cross-OS desktop control for any AI agent - the fallback execution layer.408stars