Local filesystem MCP server for securely working with Obsidian vaults
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"trsdn-obsidian-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# obsidian-mcp [](https://github.com/trsdn/obsidian-mcp/actions/workflows/ci.yml) [](https://github.com/trsdn/obsidian-mcp/actions/workflows/secret-scan.yml) [](https://github.com/trsdn/obsidian-mcp/releases/latest) [](https://www.python.org/) [](https://pypi.org/project/trsdn-obsidian-mcp/) [](LICENSE) A focused Model Context Protocol server that gives local AI clients controlled filesystem access to an Obsidian vault. It runs over stdio, works without the Obsidian application or a REST plugin, and supports read-only operation. **Use it to:** search notes, read Markdown, browse folders, and optionally create, update, move, or delete notes from any stdio-capable MCP client. ## Why Obsidian MCP? - **Local by design:** no HTTP server, API token, or Obsidian plugin. - **Vault-contained paths:** resolved paths and symbolic links cannot escape the configured vault root. - **Read-only mode:** one environment variable disables every write tool. - **Small surface area:** ten predictable tools backed by ordinary Markdown files. - **Fast search:** uses ripgrep when available, with a pure-Python fallback. > [!CAUTION] > The configured MCP client can read every Markdown note in the selected > vault. Start with `OBSIDIAN_READ_ONLY=1`, and review your model provider's > data-handling policy before exposing sensitive notes. ## Quick Start Requirements: Python 3.11 or newer and [uv](https://docs.astral.sh/uv/getting-started/installation/). The package is published to PyPI as **`trsdn-obsidian-mcp`** (the PyPI name…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.