Memory and knowledge · MCP server
Mem0 MCP selfhosted: MCP server, setup and security
Mem0 MCP selfhosted is an open-source MCP server that lets an AI agent maintain automatic memory across Claude Code sessions using self hosted mem0. Its repository has 111 stars and its last commit is from March 13, 2026 and it is licensed under MIT.
| Adoption (stars) | 20/40 | |
|---|---|---|
| Maintenance | 10/30 | |
| Framework (licence, registry, official) | 15/30 |
What Mem0 MCP selfhosted does
According to its repository: “Self-hosted mem0 for Claude Code: Qdrant vector search, Neo4j knowledge graph, Ollama embeddings and session hooks for automatic cross-session memory.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Mem0 MCP selfhosted is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #68 by stars.
Topics declared by the repository: ai-memory, anthropic, claude-code, knowledge-graph, mem0, memory.
Installing and connecting Mem0 MCP selfhosted
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python. Listed systems: macOS, Windows, Linux.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Mem0 MCP selfhosted. That does not replace reading the code.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on February 16, 2026, the elvismdev/mem0-mcp-selfhosted repository has 111 stars and 45 forks, with 6 open issues. It has more stars than 68% of the servers in the directory. Last change 7 months ago.
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Mem0 MCP selfhosted is still a modest project: read its code and compare it with the alternatives before using it.
Strengths
- Permissive licence (MIT)
Limitations
- No commit for 7 months
- Install from source
Alternatives
- Context763.6K ★
- Basic memory4.3K ★
- Hindsight53.4K ★
- Cognee32.7K ★
- Skill Seekers15.2K ★
- Honcho7.8K ★
Learn more
Frequently asked questions
How do I install Mem0 MCP selfhosted?
No package is declared in the MCP registry: clone the elvismdev/mem0-mcp-selfhosted repository, follow its README, then declare the start command in your client's MCP configuration.
Is Mem0 MCP selfhosted free?
The code is published under the MIT licence and can be used free of charge.
Is Mem0 MCP selfhosted safe?
No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.
Is it an official server?
Nothing says so: it is a project published by elvismdev on GitHub. Check who maintains it before giving it access.
What are the alternatives to Mem0 MCP selfhosted?
In the same category: Context7, Basic memory, Hindsight, and Cognee. Context7 and Basic memory score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score