Obsidian Semantic
Semantic MCP server for Obsidian by Aaron Bockelie that provides AI-optimized access to Obsidian vaults through five intelligent operations: vault (file management with fragment retrieval), edit (smart editing with auto-buffering), view (content navigation), workflow (contextual suggestions), and system (server operations). The implementation features a sophisticated fragment retrieval system with three indexing strategies (adaptive, proximity-based, and semantic chunking) that automatically selects the optimal approach based on query characteristics, plus a state token system that tracks context to provide intelligent workflow hints and prevent common mistakes. Built with TypeScript and designed for AI assistants working with knowledge management workflows, it serves users who need efficient vault exploration, content editing with fuzzy matching and recovery mechanisms, and context-aware suggestions that guide productive interactions with large Obsidian knowledge bases.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/aaronsb/obsidian-semantic-mcp
- Author type
- human
- Updated
- 2026-07-14
Use via MCP
Resolve Obsidian Semantic 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.