Memvid
This MCP server provides persistent, file-based memory capabilities for AI agents through integration with the Memvid SDK. It enables project-based memory management where agents can create isolated memory files (.mv2), store text documents with metadata, and perform hybrid semantic/lexical search across stored content. The implementation includes an optional natural language query feature that requires an OpenAI API key, allowing agents to ask questions about their stored memories. Built with TypeScript and Bun, it supports both local and home directory storage options, making it useful for applications that need to maintain context across sessions, remember previous conversations, or build knowledge bases from accumulated interactions.
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 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/khgs2411/memvid_mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Memvid 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.