"Exploring GraphRAG and HybridRAG" matching MCP servers:

MCP server for DocsMint, an AI-native knowledge workspace. It gives AI agents scoped access to search, read, create, update and organize documents using hybrid retrieval and GraphRAG.

Enables AI agents to store and retrieve project context, bugs, decisions, and session logs by reading and appending markdown files in a local Obsidian vault, without requiring any cloud services.

Enables an AI assistant to browse folders, search and read notes, create and edit them, and move notes between folders within an account. Runs locally through a supported MCP client and supports basic Markdown while refusing edits that would lose existing formatting.

Enables Claude Code to interact with Obsidian vaults by providing tools for multi-term searching, reading notes, and exploring tag-based relationships. It allows users to query, analyze, and manage their personal knowledge base directly through natural language.

A learning-focused MCP server that demonstrates core MCP concepts through a simple notepad application, enabling users to create, update, delete, and search notes while exploring tools, resources, and prompts functionality.

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 local MCP clients to list, read, write, and search notes in an Obsidian vault via an HTTP server running inside Obsidian.

MCP server for Ultrathink: save and search your knowledge base from Claude Desktop, Claude Code, and any MCP client.

Enables coding agents to search and read curated project memory before exploring code, and to record durable findings as append-only events for later Librarian auditing.

Enables synchronization and management of FoundryVTT journal entries within a Notion Story Bible, including media export and conflict resolution tools. It provides a Model Context Protocol interface for LLMs to preview, apply, and monitor data mirroring between tabletop RPG platforms and digital databases.

Enables AI assistants to search, read, and browse Bear notes directly from your local Bear database. Supports searching by title, content, or tags, opening specific notes, and exploring tag-based organization.

Enables searching and exploring handwritten reMarkable notebooks through a natural conversation with Claude Desktop, with full-text search, classification, and source citations.

An MCP Server that leverages notes written in Markdown, tailored for developing Cisco Nexus Dashboard applications using the REST API.

A lightweight Python-based MCP server for managing recipes and favorite collections. It provides a structured service-style layout to handle recipe business logic, persistence, and external client interactions.

Enables creating, linking, tagging, searching and exploring atomic notes that form a networked knowledge graph, with bidirectional semantic link types and markdown files as the source of truth. Supports knowledge creation, exploration and synthesis through Claude and other MCP-compatible clients.

Enables Claude and other MCP-compatible clients to create, link, tag, search, and update atomic notes stored as Markdown files, building a bidirectional knowledge graph with semantic relationships. Also supports exploring and synthesizing that graph through tools that surface linked, similar, central, and orphaned notes.

Provides AI clients with per-project todo management and persistent context notes via MCP, enabling task tracking and resume summaries.

Enables AI agents and users to manage workspace files, monitor system metrics, take persistent notes, and retrieve weather data via MCP tools and resources.

Enables creating, linking, searching, exploring, and synthesizing atomic notes as a knowledge graph through MCP-compatible clients such as Claude. Supports tags, note types, semantic relationships, Markdown storage, and an SQLite index for efficient traversal.

Cortex is a Claude Code plugin that gives Claude persistent memory across sessions. A background miner extracts durable lessons (decisions, conventions, bug fixes, preferences) from your completed sessions, stores them as markdown in an Obsidian vault, and automatically surfaces relevant ones at the start of each new session via a query-tailored briefing.