MCP server for searching and reading an Obsidian vault with hybrid ranking based on BM25, graph centrality, and usage history. It tracks file retrievals over time so search results adapt to what the user actually reads and uses.
From the registry: Usage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking.
$ pip install hebbian-vaultPlease install the `hebbian-vault` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.10+** — Python 3.10 or newer is required to run hebbian-vault.
- **Install hebbian-vault** — Install the MCP server package from PyPI. Run: `pip install hebbian-vault`
- **Have an Obsidian vault available** — You need a local Obsidian vault path to point the server at. Wikilinks are recommended for graph features.
Canonical MCP server config (stdio transport):
- command: `hebbian-vault`
- args: ["--vault","<path-to-your-obsidian-vault>"]
- optional environment variables:
- `HEBBIAN_VAULT_LICENSE`: Pro license JWT for enabling Pro features such as inline tracking. Not required for standard usage. (example: `<your-license-jwt>`)
Note: Default transport is stdio. The server also supports HTTP via --transport streamable-http and --port <port>, but the README does not provide a canonical URL shape for client configuration, so the portable default stdio configuration is preferred. Optional CLI flags include --inline-tracking for Pro users and --license-key <your-license-jwt> as an alternative to the HEBBIAN_VAULT_LICENSE environment variable.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.HEBBIAN_VAULT_LICENSErequiredEnvironment variable for providing a Pro license JWT.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Trending hip-hop artist momentum scores across four cultural dimensions.
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.