"dbt" matching MCP servers:

Provides tools for storing, searching, and managing memories with knowledge-graph enriched context via Hydra DB's agentic memory.

Enables persistent, full-text-searchable context for AI agents, including session tracking, event logging, todo management, and tagged context retrieval.

Enables AI agents to query live schema, lineage, and query-context across data warehouses, dbt projects, orchestration systems, and BI tools via MCP tools.

Provides a local, persistent context database for AI tools via MCP, enabling them to recall user preferences, decisions, and experiences across sessions. It is fully local with optional sync, and works with any MCP client.

Turns your Readwise library into a blazing-fast semantic search engine with a streaming MCP server for LLM clients, supporting vector search, nightly syncs, and deployment on serverless platforms like Vercel.

Provides tools for semantic search, CRUD, verification, and reindexing of documents in a local vector-based knowledge base, usable via HTTP or stdio.

Enables Claude to read, write, and search markdown notes stored in a private git repo via an MCP server integrated with Silverbullet editor.

A temporal knowledge graph system that enables users to record and query architectural decisions, implementation patterns, and project failures. It integrates with Claude to provide hybrid search, timeline tracking, and automated knowledge gap detection using graph analysis.

A lightweight vector-based memory system for AI agents with tools to store, semantically search, and delete memories, using your own embedding model.

Stores and retrieves project context using OpenAI vector stores, enabling AI editors to remember and recall project knowledge across sessions.

A multi-vendor database management tool that enables LLMs to query, migrate, and synchronize schemas across SQL engines like PostgreSQL, MySQL, and Oracle. It features persistent knowledge management for storing AI-generated context about database structures and business rules.

A vector-DB MCP server that gives Claude conversational memory by storing solved problems and solutions as vectors and retrieving relevant ones when a new request resembles a past solution.

Enables security teams to determine which ATT&CK techniques lose detection coverage when telemetry sources are removed, by computing set differences over a Sanity content graph and consulting a knowledge base via two Context MCP endpoints.

Enables AI coding agents to persistently store and retrieve conversation history with hybrid semantic and keyword search, cross-encoder reranking, session filtering, and archiving through MCP tools.

Enables AI assistants to access Fathom meeting recordings, summaries, transcripts, teams, and webhooks through the Model Context Protocol.

Central user-state database MCP server with durable profile facts and live virtual sensors (stress, room intensity) with configurable smoothing, readable by any agent or smart-home service.

Feynman's twelve-problems method as an MCP server — a persistent set of long-running problems plus an evoke loop that tests each new trick against all of them. Local, TypeScript, no LLM inside, no API key.

Enables file-based knowledge management with ranked keyword and semantic hybrid search, allowing AI agents to learn from documents and recall relevant knowledge as a persistent memory tool.

Zero-config graph DB for builders, AI agents, and SaaS teams who move fast

Enables storing and retrieving semantic memories using LanceDB vector database, with tools to add memories and search by similarity.