"Collaboration Between Multiple AIs via MCP (Master Control Program)" matching MCP servers:

Exact recall from a plain-text index you keep: recall, find, tags, timeline over stdio. Read-only by default; ais --mcp rw adds saving; no delete at any setting. Encrypted values stay opaque to the agent

Enables AI agents to read and write Markdown notes in an Obsidian vault over the Model Context Protocol, with concurrency-safe edits and optional write restrictions.

An MCP server that treats Obsidian vaults as knowledge graphs, enabling AI agents to traverse wikilinks, assemble token-budgeted context, and search with backlink awareness.

Enables secure synchronization of ChatGPT, Claude, and Obsidian via Supabase as the source of truth, with OAuth protection and proposal-based AI changes.

Provides semantic search, note retrieval, source explanation, daily digests, and health checks for a local Obsidian vault, enabling MCP clients like Claude Desktop and Claude Code to query the second brain via natural language.

Connects AI assistants to Obsidian vaults via the Local REST API to search notes, retrieve content, and perform semantic searches. It features self-healing multi-URL connectivity and supports both stdio and HTTP transports for flexible deployment.

Gives AI assistants a persistent memory across conversations, allowing them to remember user preferences, notes, and facts between chats.

Create and read burn-after-read encrypted notes. AES-256-GCM E2E encryption with self-destructing URLs for secure credential handoff between users and AI agents.

Provides full access to Hookmark on macOS, enabling users to create and manage bidirectional links between files, URLs, emails, and notes. It supports searching bookmarks, connecting items, and retrieving links from active applications through natural language.

Reading and writing Apple Notes with native Markdown conversion

Enables interaction with multiple Obsidian vaults through natural language, supporting note operations, search, and vault management with both REST and filesystem backends.

Control Apple Music via natural language from Claude Code, with the ability to mark tracks and accumulate reactions in an Obsidian Vault.

Local-first personal wiki and memory server for AI agents. MCP clients can capture knowledge, retrieve context, read and maintain source-backed wiki pages, and carry project context between sessions.

Enables LLMs to search and retrieve personal journal entries using RAG, and add new entries with date filtering and multiple vector stores.

Gives AI assistants direct control of a reMarkable tablet over SSH, enabling listing notes, uploading PDFs, exporting handwriting, and writing on pages via a single MCP tool.

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.

MCP server for Rootr markdown knowledge collaboration. Provides 27 tools for reading, writing, searching, and managing documents, issues, logs, and webhooks via natural language.

A shared working-state layer for AI coding tools that provides a persistent notebook for decisions, tasks, and handoffs, enabling seamless context sharing between Claude, Cursor, and other MCP clients.

Enables AI assistants to search, read, create, and modify Docmost pages, spaces, and comments via REST and Yjs WebSocket collaboration.

Local-first MCP server for navigating and maintaining arbitrary hierarchical documentation with flexible node structure, raw content, and multiple parents, leaving navigation decisions to the connected LLM.