Mem0.ai Memory Manager
The Mem0 MCP Server provides AI assistants with access to Mem0.ai's memory management system through a cognitive-inspired architecture that organizes memories into different types based on their nature, persistence, and purpose. Built with Python using the AsyncMemoryClient from mem0ai, it implements short-term memory operations (conversation, working, attention) and long-term memory types (episodic, semantic, procedural) with support for selective memory filtering, custom categories, and knowledge graph relationships. The server includes advanced features like memory feedback mechanisms and custom instructions, making it ideal for users who need persistent, structured memory across conversations for personal preferences, project knowledge, or research workflows.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/ryaker/mcp-mem0-general
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Mem0.ai Memory Manager 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.