"Vector Database" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
A portable knowledge-graph memory you pass in and get back. No database. 4 of 6 free.
CWI Discovery Engine is the sync-licensing discovery layer for AI agents: natural-language brief in, licensable tracks with verified ISRCs and one-signature clearance out. 29 MCP tools (find_tracks_for_brief leads). For general ISRC metadata lookup, we defer to MusicBrainz — we are the licensable-track discovery layer, not a general database.
Exact, shared memory for multiple AI agents. Azquo is a hierarchical database: each fact is stored once in hierarchies that always total correctly, every write is attributed to the agent and person behind it, and any figure can be traced back to the file and cell it came from. There is no schema to design first - agents build and reorganise the structure themselves - and people work with the same data live in Microsoft Excel. Suited to finance and insurance work, where figures must stand up to review.
Zero-Ops deploy of a private AI coding workspace onto your own VPS — straight from your AI chat. Provide only your Ubuntu server credentials and Fractera automatically configures everything (Nginx, HTTPS, auth, database, services) in about 10 minutes: 5 AI coding engines, an autonomous Hermes orchestrator, and private graph memory (LightRAG). No terminal, no DevOps. IP-first and free; a custom domain with HTTPS is an optional later step.
Cobrain is a hosted Markdown brain your AIs share. Connect Claude, ChatGPT, Claude Code, Codex or any MCP client once (remote MCP with OAuth, no API keys to paste) and they all read and write the same notes. Share one folder with a teammate, read-only or read-write, and their AI reads it too. Permissions are enforced in the database, the same for the web app and for AIs; writes are version-checked so two AIs can't silently overwrite each other. Plain .md, exportable, EU-hosted. Free plan available.
Database for your AI agent. Turn its output into data, docs, skills, and apps you can actually use.
A personal RAG database you build from chat, so AI creates work that sounds like you.
Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.
D&D and TTRPG campaign manager for GMs: your AI reads and writes a live, typed campaign database.
AI Incident Database (AIID) MCP
Grimoire turns your TTRPG campaign into a structured, queryable database and knowledge graph and exposes it to any MCP-compatible AI client. Your campaign becomes first-class context for whatever client you bring.
Memwyre is an MCP-native persistent memory layer for AI agents, synchronizing context across Claude Code, Cursor, VS Code, and OpenClaw. Built with a high-precision retrieval architecture (dense vector search, BM25, and cross-encoder reranking), Memwyre achieves a benchmarked 73.1% accuracy on the Long-Context Memory (LoCoMo) benchmark. It provides secure, isolated knowledge vaults with dedicated tools (search_memwyre, save_memory, list_memories) to save and recall structured project decisions.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Zero-key temporary JSON database for agents: one tool call, no signup, no OAuth, no API keys.
MemoryOracle - 10 agent memory tools: vector store, recall, summarization, redaction.
MCP memory server with shared team workspaces, typed knowledge chunks (decision, finding, convention, state, question, reference), role-based access, and cross-tool support for Claude, Cursor, and Codex. The only MCP memory server built for engineering teams. Features automatic deduplication, two-layer retrieval (LLM KB selection + hybrid vector/BM25/RRF fusion), a web dashboard with knowledge graph visualization, and attribution tracking. Zero server-side LLM costs.
Make your knowledge agent-ready. Connect docs from Confluence, Notion, GitHub, Dropbox, or Google Drive — any AI agent searches them via one MCP endpoint. 3 retrieval modes: vector search, broad search, and full document access. The agent decides how deep to dig.
Provenance-first database for teams and agents: every value carries sources, rules and coverage.
Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.
An agent-native database over MCP: shared, validated, structured records in every AI chat.
Semantic search over MINDSET's brand strategy topic database, plus its system prompt.
Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.
