No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by elvismdev · MCP Server · ★ 106
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mem0-mcp-selfhosted safe to install? View the security audit →
mem0-mcp-selfhosted Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama, with your choice of Anthropic (Claude) or Ollama as the main LLM. Uses the package directly as a library, supports both Claude's OAT token and fully local Ollama setups, and exposes 11 MCP tools for full memory management. Prerequisites Python = 3.10 and uv. Authentication: The default setup uses Claude (Anthropic) as the LLM for fact extraction. No API key needed, the server automatically uses your Claude Code session token. For fully local setups, set . See Authentication for advanced options. Quick Start Default (Anthropic) Add the MCP server globally (available across all projects): bash cla
| Stars | 106 |
| Forks | 45 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 75.1492776289467/100 |
| Open Issues | 12 |
| Last Updated | 2026-03-13 |
| Created | 2026-02-16 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~19k |
These tools work well together with mem0-mcp-selfhosted for enhanced workflows:
Looking for a mem0-mcp-selfhosted alternative? If you're comparing mem0-mcp-selfhosted with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Persistent memory for AI coding agents
📜 An MCP server for conversation history search and retrieval in Claude Code
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo
Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (Fa
MCP SSH Server: 37 tools for remote SSH management | Claude Code & OpenAI Codex | DevOps automation, backups,
This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure whe
Explore other popular mcp server tools:
mem0-mcp-selfhosted is Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama while using Claude as the main LLM.. It is categorized as a MCP Server with 106 GitHub stars.
mem0-mcp-selfhosted is primarily written in Python. It covers topics such as ai-memory, anthropic, claude-code.
You can find installation instructions and usage details in the mem0-mcp-selfhosted GitHub repository at github.com/elvismdev/mem0-mcp-selfhosted. The project has 106 stars and 45 forks, indicating an active community.
mem0-mcp-selfhosted is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to mem0-mcp-selfhosted on Agent Skills Hub include omega-memory, claude-historian-mcp, roampal-core. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: