Obsidian Index
This MCP server, developed by Tom Savage, provides semantic search capabilities over an Obsidian vault and exposes recent notes as resources. Built with Python and leveraging libraries like DuckDB and sentence-transformers, it offers tools for indexing and searching notes, as well as watching for changes in the vault. The implementation stands out by using semantic search to find relevant notes and exposing them through an 'obsidian://' URL scheme. It's particularly useful for researchers, writers, and knowledge workers who want to integrate their personal knowledge base with AI assistants, enabling context-aware interactions and dynamic retrieval of relevant information from their Obsidian vaults.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/tcsavage/mcp-obsidian-index
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Obsidian Index from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.