← Back to directory
E

enquire-mcp

Community
Your Obsidian vault becomes the private memory and document intelligence layer for every AI agent.
GitHub source repository ↗
★ 33 Stars Category · Other Popular Source revision 0db770a4dca3
67FMRS · C

enquire-mcp is a feature-rich Obsidian MCP server prioritizing local-first and privacy, offering powerful hybrid retrieval and RAG. It's suitable for professionals and privacy-conscious users. Note its extensive features require configuration and include experimental elements; consider waiting for stable release.

Reliability
10/20
Security and permissions
16/20
Maintenance
12/20
Documentation
15/20
Setup experience
14/20
Read the FMRS scoring method →

enquire-mcp is a local-first MCP server that turns your existing Obsidian vault (including Markdown, PDFs, Canvas, and Bases) into a persistent, queryable knowledge database for any MCP-compatible AI agent. It features hybrid retrieval (BM25, TF-IDF, multilingual embeddings), local BGE reranking, HNSW indexing, freshness-aware search, and cited sources. It's read-only by default with zero cloud calls during serve, and supports 50+ languages.

Tools

obsidian_search
Performs hybrid retrieval (RRF-fused) returning cited notes and PDFs.
obsidian_hyde_search
Performs HyDE-augmented search for better semantic recall.
obsidian_search_text
Searches notes by textual content.
obsidian_full_text_search
Full-text search using FTS5.
obsidian_semantic_search
Semantic search based on embeddings.
obsidian_embeddings_search
Direct embedding vector search.
obsidian_find_similar
Finds similar notes to a given note.
obsidian_resolve_wikilink
Resolves a wikilink to its target note.
obsidian_get_backlinks
Gets backlinks pointing to a note.
obsidian_get_outbound_links
Gets outbound links from a note.
obsidian_get_note_neighbors
Gets neighbors of a note (directly linked notes).
obsidian_get_unresolved_wikilinks
Gets unresolved wikilinks in a note.
obsidian_find_path
Finds a path between two notes in the graph.
obsidian_get_communities
Detects topical communities in notes (GraphRAG-light).
obsidian_frontmatter_get
Gets frontmatter of a note.
obsidian_frontmatter_search
Searches notes by frontmatter fields.
obsidian_dataview_query
Executes a Dataview query.
obsidian_list_tags
Lists all tags across notes.
obsidian_read_note
Reads the content of a note.
obsidian_list_notes
Lists notes in the vault.
obsidian_get_recent_edits
Gets recently edited notes.
obsidian_stale_notes
Lists notes that are stale or outdated.
obsidian_open_questions
Lists open questions or todos.
obsidian_context_pack
Generates a context pack of related notes.
obsidian_chat_thread_read
Reads a chat thread file.
obsidian_open_in_ui
Opens a note in the Obsidian UI.
obsidian_stats
Gets statistics about the vault.
obsidian_read_pdf
Extracts text from a PDF, with page citations.
obsidian_list_pdfs
Lists PDFs in the vault.
obsidian_ocr_pdf
Performs OCR on a PDF page.
obsidian_read_canvas
Reads a Canvas file's content.
obsidian_list_canvases
Lists Canvas files in the vault.
obsidian_list_bases
Lists Bases (databases) in the vault.
obsidian_read_base
Reads a Base's content.
obsidian_query_base
Queries a Base.
obsidian_create_note
Creates a new note.
obsidian_append_to_note
Appends content to a note.
obsidian_rename_note
Renames a note.
obsidian_replace_in_notes
Replaces text in notes.
obsidian_archive_note
Archives a note.
obsidian_frontmatter_set
Sets frontmatter of a note.
obsidian_chat_thread_append
Appends to a chat thread.
obsidian_lint_wiki
Checks for wikilink issues.
obsidian_paper_audit
Audits papers or documents for completeness.
obsidian_validate_note_proposal
Validates a note proposal.
obsidian_mark_useful
Marks retrieved results as useful for feedback loop.

Setup

  1. Install globally: npm install -g @oomkapwn/enquire-mcp. 2. Add MCP config to your client (see docs or use enquire-mcp configure). 3. Example config in install_config.
claude_desktop_config.json
{
  "mcpServers": {
    "obsidian": {
      "command": "npx",
      "args": ["-y", "@oomkapwn/enquire-mcp", "serve", "--vault", "/path/to/vault"]
    }
  }
}

Fit and risk

Best for

  • Privacy-conscious users who want local AI memory.
  • Users with multiple AI clients needing a unified memory layer.
  • Obsidian enthusiasts who want to keep Markdown portable.

Not for

  • Users requiring cloud sync or remote access without setup (unless using HTTP transport with proxy).
  • Those wanting zero technical configuration or model download.
  • Users needing only a simple global search without AI integration.

Required permissions

  • Read access to the Obsidian vault directory (required).
  • Create and edit notes (only when `--enable-write` is set).
  • Download models and language packs (only via setup, build-embeddings, install-model, install-ocr-lang commands).

Risks and side effects

  • Prompt injection: Vault content may contain instructions, so prompt must state content is data, not instructions.
  • Write operations: If write enabled, accidental modification possible; use dry_run and version control.
  • Local model download: First-run downloads (approx 118MB) require network.
  • Path traversal: Ensure vault path is correct and clients cannot access outside vault; server has validation.

Troubleshooting

  1. 1. Verify vault path exists.
  2. 2. Check MCP config uses absolute paths.
  3. 3. Run `enquire-mcp doctor` for readiness.
  4. 4. Ensure firewall allows local process (for stdio).
  5. 5. Check version compatibility; README and CHANGELOG indicate potential issues with Claude Desktop.

Use cases

Provide long-term memory for AI agents across sessions, preserving project history, decisions, and knowledge.
Serve as a personal second brain with multilingual, multi-format semantic search.
Enable agentic RAG and context engineering with interpretable scores and citations.

Supported clients

Claude DesktopPartial support
Claude CodeFull support
CursorPartial support
VS CodePartial support
ChatGPT (custom GPT)Partial support
CodexPartial support
OpenClawPartial support