"Semantic layer for SQL query execution with dimensions and measures" matching MCP servers:

Lets AI agents retrieve source-linked passages from a local folder of Markdown notes or an Obsidian vault, optionally following the explicit links between notes, and can also fetch passages from pinned public GitHub files you configure. It returns bounded evidence packets with original text, file paths and hashes so agents can answer from your material rather than generating content themselves.

A persistent memory layer for Claude Desktop that enables semantic search across your entire Obsidian vault using local embeddings and PostgreSQL + pgvector.

Enables semantic search over markdown files to find related notes by meaning rather than keywords, and automatically detect duplicate content before creating new notes.

Read-only semantic retrieval for agents that need to find the right Obsidian note without write access.

Enables complex queries over data on the DANDI Archive and provides a system for managing text notes. It features tools for note creation, resources for note access via custom URIs, and prompts for generating summaries.

Enables filtered, read-only querying of a Notion audit trail and action queue as four native tools (filtered lists and single-row lookups), with enum parameters validated against the live database schema and errors that report allowed values. It never writes to Notion, returns flat JSON rows, and keeps the integration token server-side.

A server that consolidates 21+ Obsidian tools into 5 intelligent operations (vault, edit, view, workflow, system) with contextual workflow hints to help AI agents effectively interact with Obsidian.

A native Nextcloud app that exposes the instance as an MCP server so Claude and other MCP clients can read, search, and (with admin-granted permissions) edit files, notes, calendars, Deck cards, and Talk conversations. It runs inside Nextcloud with OAuth or app-password sign-in, applying each user's own Nextcloud permissions and admin-controlled per-operation grants.

Persists Claude Code sessions to Notion as team memory, enabling queryable recall of decisions, work state, and project architecture.

A live MCP server that connects AI assistants to a running Obsidian instance, enabling full app automation including reading notes, clicking UI elements, managing plugins, and executing JavaScript.

A robust MCP server that transforms OneNote notebooks into an AI-accessible knowledge base for Gemini Spark, enabling natural language queries to list, read, and search notes via Microsoft Graph API.

Connects AI assistants to an Obsidian vault as a semantic knowledge graph, enabling graph navigation, semantic search, and content operations through MCP.

MCP server for Obsidian vaults, optimised for Cursor agents — safe note editing, lean tool surface, direct filesystem access.

MCP server to interact with Obsidian via the Local REST API community plugin.

Interacts with LogSeq via its API.

A TypeScript-based MCP server that enables users to query financial news, stock data, and index information while managing text notes with creation and summarization capabilities.

Enables notes management, weather and news search, document ingestion and RAG-based semantic search using GroundX, with OpenAI GPT integration for summarization and completions.

Connects to Microsoft OneNote desktop via COM API, exposing 27 tools for hierarchy, page CRUD, search, rich content, export, health checks, and more. Enables natural-language control of OneNote without API keys or embedded AI providers.

Enables MCP clients to search and read recorded meeting data, including transcripts, notes, action items, and participants, from Walkie's local database.

Enables AI assistants to intelligently save, organize, and retrieve content through Mem.ai's knowledge management platform. Supports creating notes, collections, and AI-powered content processing with automatic organization.