Mem0 (Long-Term Memory)
MCP-Mem0 is a server implementation that integrates Mem0's long-term memory capabilities with AI agents through the Model Context Protocol. Developed by Cole Medin, it provides three essential memory management tools: storing information with semantic indexing, retrieving all stored memories, and finding relevant memories using semantic search. The server supports multiple LLM providers (OpenAI, OpenRouter, Ollama) and uses PostgreSQL for vector storage, making it particularly valuable for applications requiring persistent memory across conversations, such as personal assistants, knowledge management systems, or any AI agent that needs to recall past interactions and information.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/coleam00/mcp-mem0
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Mem0 (Long-Term Memory) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.