Obsidian is a powerful knowledge base and note-taking application that works on top of a local folder of plain text Markdown files, emphasizing linking and connecting ideas to help build your personal knowledge management system.
Provides full access to an Obsidian vault, allowing AI agents to search, read, write, manage structured memory, query backlinks, and work with daily notes.
Standalone MCP server for Obsidian vaults - hybrid search (FTS5 + vector + cross-encoder reranking), images and PDFs in agent-readable form, Kanban-aware tasks (Tasks-plugin + Dataview formats), structured memory with topic recall, fine-grained read/write tools for optimal token efficiency, and link graph support. Run locally, self-host, or one-click deploy for remote access. OAuth 2.1.
10
33
51 npm
26
MIT
Why this server?
Provides integration with Obsidian vaults, enabling AI assistants to read and write notes within an Obsidian vault.
tdmcp is an open-source (MIT) Model Context Protocol server for TouchDesigner. You describe a visual in plain language and your AI assistant builds the real node network inside TouchDesigner, checks it for errors, and shows a preview — it ships an embedded operator knowledge base so the model uses real operators instead of guessing. TypeScript codebase, runs locally.
The first cognitive memory server for AI assistants, providing persistent memory, knowledge graph, identity awareness, contradiction detection, and belief tracking across sessions.
38
126 npm
1
MIT
Why this server?
Allows interaction with Obsidian via the Local REST API community plugin. Capabilities include listing files in vault, retrieving file contents, searching across vault files, patching content into existing notes, and appending content to new or existing files.
Enables AI agents and MCP clients to start each session with a pre-assembled context pack of the project's Markdown notes, decisions, rules, Git and tracker state, and to write progress and decisions back as dated logs. Context is gathered locally by lookups and queries rather than model calls, so different tools like Claude Code, Codex, and Antigravity share the same memory without spending tokens on retrieval.
15
111 PyPI
1
Apache 2.0
Why this server?
Provides integration with Obsidian-compatible markdown vaults. It supports Obsidian-style wikilinks, tags, Obsidian Tasks date formats (Dataview and emoji), daily notes, templates, and a Kanban board stored in task lines. Agents can create, read, list, and search notes, manage tasks, move tasks between columns, set start/due dates, and toggle task completion while preserving Obsidian-friendly markdown.
Local MCP server for plain Markdown notes: list, read, create and search notes, and manage their tasks and Kanban board (move cards, toggle tasks, set start and due dates).
2
9
76
MIT
Why this server?
Can be run alongside an existing Obsidian vault as a governed memory layer, complementing current notes without replacing them.
MCP server that turns any audio or video source into structured, searchable intelligence for agents, enabling download, transcription, semantic search, speaker identification, and more.
22
4
MIT
Why this server?
Allows agents to use an Obsidian vault as long-term memory, providing tools to semantically search, read, write, and maintain Markdown notes, including backlinks, graph overview, broken links, and vault health metrics.
Turns a plain-Markdown Obsidian vault into a second brain that any MCP-speaking coding agent can search, read, extend, and maintain, using swappable SQLite, Qdrant, or markdown memory backends with automatic re-indexing and wiki-link graph navigation. Exposes read, write, and index tools plus an operator CLI for health, linting, and graph export.
