Obsidian MCP (pgvector + Ollama, self-hosted)
Related Servers
Alternatives to Obsidian MCP (pgvector + Ollama, self-hosted)
- AlicenseAqualityAmaintenanceStandalone MCP server for Obsidian vaults - hybrid search (FTS5 + vector + cross-encoder reranking), images and PDFs in agent-readable form, Kanban-aware tasks (Tasks-plugin + Dataview formats), structured memory with topic recall, fine-grained read/write tools for optimal token efficiency, and link graph support. Run locally, self-host, or one-click deploy for remote access. OAuth 2.1.33291 npm20MIT
Related Servers
- AlicenseNot gradedqualityBmaintenanceSelf-hosted MCP server for private Obsidian vaults on GitHub, exposing tools to search, read, write, and analyze Markdown notes and their link graph.MIT
- AlicenseNot gradedqualityDmaintenanceSelf-hosted MCP server that provides embedding-powered semantic search with graph context over Obsidian vaults, supporting multiple vaults, local embeddings, and a web dashboard.MIT
- AlicenseNot gradedqualityAmaintenanceMCP server exposing fast full-text and semantic search over an Obsidian vault, plus safe structured note read and write access for Claude.2Apache 2.0
- AlicenseNot gradedqualityAmaintenanceLocal-first MCP server for retrieval over markdown wikilink vaults, offering hybrid vector+lexical search, note reading, neighbor expansion, and recent activity tracking with fully local embeddings and no network egress.MIT
- AlicenseBqualityCmaintenanceHeadless semantic MCP server for Obsidian, Logseq, Dendron, Foam, and any markdown folder. Features built-in hybrid semantic search, surgical AST editing, template scaffolding, zero-config local embeddings, and workflow tracking.520 npm12MIT
- FlicenseNot gradedqualityCmaintenanceSelf-hosted MCP server that provides remote AI clients with read and write access to Obsidian vaults over HTTPS without needing the Obsidian desktop app running.2-
TDQS
Scored across 25 tools
Most tools are well-separated by their primary function (read vs. write, note vs. file, search vs. link analysis). However, there is some overlap between read_note and read_file, and between create_note/edit_note vs write_file, though the descriptions make the distinction clear. Also, find_related and semantic_search are similar but differentiated by source, and get_neighborhood vs find_related is clarified.
The naming is mostly consistent with a verb_noun pattern (list_notes, create_note, edit_note, delete_note, read_file, write_file, etc.). Minor deviations include request_upload, request_download (not verb_noun but consistent with each other), and check_upload. The mix is readable and intuitive.
With 25 tools, this is at the high end of the 'well-scoped' range but remains justified for a comprehensive vault management server. Each tool covers a distinct operation (notes, files, search, links, transfers), and the count is appropriate for the breadth of features offered. Slightly over the typical 3-15 range but not excessive.
The server provides a complete lifecycle for both notes and files: create, read, edit/update, delete, plus advanced features (frontmatter mutation, move, search, link analysis, upload/download, import). The coverage is comprehensive with no obvious dead ends. Even edge cases like stale indexes and non-markdown files are handled.