A safety-constrained MCP bridge for connecting AI agents with Obsidian, featuring reusable skill templates and controlled read/write workflows.
Skill Codex
Incrementally integrate a user-provided batch of recent learning, project progress, debugging, practice, and observations into an existing Obsidian knowledge base. Use for requests to organize or synchronize a heterogeneous recent batch. Preserve confirmed evidence attribution, but do not initiate method attribution…
Skill Codex
Review post-training evidence and project practice to assess a method's recorded state, autonomy trajectory, outcomes, transfer, and readiness for a next level without changing it. Use when the user asks whether a method was practiced, whether progress or transfer occurred, how evidence should be attributed, or…
Skill Codex
Control how much help to provide during an active capability-building task without stealing the user's core reasoning opportunity. Use for programming, debugging, database, research, engineering, or method-transfer practice when the user asks to train, receive hints, work independently, or get review-only feedback. Do…
Skill Codex
Search, read, compare, recall, and synthesize information that may already exist in the user's Obsidian knowledge base. Use for read-only requests to find prior notes, compare records, restore history, or synthesize existing knowledge. Do not use as the primary workflow for active training, a Vault write request, or a…
Skill Codex
Safely maintain one knowledge item or a small focused set in the user's Obsidian knowledge base. Use for requests to record, update, organize, or connect a focused item. Prefer existing notes, obey the live Review or Direct preference, and use only approved Obsidian MCP write tools. In Review mode, generate and show…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: