Memory
Personal long-term memory MCP server that provides persistent memory storage across different AI clients like Cursor, Claude Desktop, and Windsurf using semantic search and RAG capabilities. Built by @pulik_io and hosted on Cloudflare Workers with D1 database and Vectorize for storage, the implementation generates unique user identifiers stored locally in browsers and provides a web interface for viewing, editing, and managing stored memories. Designed for users who want consistent context and preferences maintained across multiple AI applications without losing conversational history when switching between different MCP clients, enabling truly persistent AI relationships that remember past interactions, user preferences, and accumulated knowledge over time.
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
- database
- Source
- PulseMCP
- Repository
- github.com/puliczek/mcp-memory
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve 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.