Obsidian MCP Server

Bound Obsidian Wiki MCP server and local runtime CLI for grill-adapter. That is what the obsidian mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

A host-agnostic Claude Code and Codex plugin that adds a sectioned, cross-repo project wiki, source-of-truth verification, and break-loop debugging retrospectives as standalone skills, agent roles, and hooks. It never patches a host skill: it wires into your workflow through a project convention block (CLAUDE.md or AGENTS.md) and the plugin's own hooks, so host upgrades can't break it.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What it needs from you

• Claude Code or Codex (CLI/app) - Python 3.9+ - Node.js ≥ 20 (to run the bundled Wiki MCP servers; the plugin ships prebuilt bundles — nothing to build) - npm (for the published grill-adapter CLI or the Obsidian runtime CLI)

How it compares

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.