"Arc" matching MCP servers:

An MCP server providing semantic memory storage and retrieval using vector embeddings powered by LanceDB and Google Gemini. It supports multi-tenant isolation and bucket-based organization for managing structured memories through natural language queries.

ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vector Embeddings.

Semantic vector DB as an MCP server for Claude Code — SQLite + FTS5 + local ONNX embeddings. Gives Claude persistent, searchable project knowledge across conversations.

Enables semantic search and AI-powered analysis of Outlook emails using RAG-based natural language queries and Vision AI for architectural documents, with specialized support for AEC workflows.

Enables semantic search and question-answering over semiconductor component data stored in Excel files using ChromaDB vector database and HuggingFace language models through a RAG pipeline.

A cognitive memory system for MCP that provides hybrid retrieval, memory layers, entity graph, and 83 tools for recall, remember, codebase scanning, and more.

Headless geometric memory engine for AI agents — no Vector DB, no cloud, no API key. Store and retrieve by meaning using native Vector Symbolic Architecture (NVSA) math over O_DIRECT NVMe mapping. Runs entirely on your machine via MCP.