Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
Enquire is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
27
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user enquire-mcp '--' npx -y @oomkapwn/enquire-mcp
# 2 — ask your agent for something these tools do
# obsidian_full_text_search, obsidian_list_notes, obsidian_read_note and 43 more
Enquire costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
OOAll 1 server
oomkapwn1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Enquire as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user enquire-mcp '--' npx -y @oomkapwn/enquire-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
46 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
BM25-ranked full-text search backed by a SQLite FTS5 inverted index. Returns chunk-level hits with snippet excerpts. Hyphenated tokens (e.g.
No parameter schema on file.
List notes in the vault. Filter by tag, folder, or modified-since date. Returns title, path, frontmatter, tags, and mtime — newest first.
No parameter schema on file.
Read a note by relative path or by title (filename without .md). Default
No parameter schema on file.
Resolve an Obsidian [[wikilink]] (or ![[embed]]) to a vault file. Handles aliases (Note|alias), sections (Note#Heading), block refs (Note^block), and ../-relative paths.
No parameter schema on file.
Case-insensitive token search across all notes. Default mode
No parameter schema on file.
List notes ordered by most recent modification. Useful for picking up where work was left off.
No parameter schema on file.
List notes not edited in N days (forgetting-aware staleness), oldest first. Use to surface facts that may be outdated before relying on them, or to pick notes to refresh. Cheap mtime-only scan; returns path / title / mtime / age_days.
No parameter schema on file.
List every note in the vault that links (or embeds) the target note. Returns ranked hits with snippets and link kind (wikilink/embed/mixed).
No parameter schema on file.
List every unique tag in the vault with usage counts (frontmatter vs inline). Sorted by count desc.
No parameter schema on file.
Run a Dataview-style query. Grammar: (LIST | TABLE col1, col2) FROM (
No parameter schema on file.
Find every [[wikilink]] (and ![[embed]]) in the vault whose target does not resolve to a file. Useful as a vault-hygiene utility — broken links, typos, notes you intended to create.
No parameter schema on file.
List every link this note points to — wikilinks and (optionally) embeds, with each one
No parameter schema on file.
No parameter schema on file.
Given a note, return up to N other notes that are
No parameter schema on file.
Return a note
No parameter schema on file.
No parameter schema on file.
Comprehensive vault-hygiene check inspired by Karpathy
No parameter schema on file.
Walks every note for lines matching deferred-thinking markers —
No parameter schema on file.
For each note tagged
No parameter schema on file.
Multi-hop graph traversal: BFS from
No parameter schema on file.
Returns an
No parameter schema on file.
Lists
No parameter schema on file.
v3.4.0 — Computes structural communities over a complete resource-bounded vault wikilink graph via greedy modularity optimization (single-phase Louvain). Returns exact total/eligible/returned community and member counts, membership-path JSON UTF-8 byte receipts, explicit truncation receipts,
No parameter schema on file.
v3.2.0 — Lists
No parameter schema on file.
v3.2.0 — Parses a
No parameter schema on file.
v3.2.0 (extended in v3.5.0) — Runs a
No parameter schema on file.
Parses one
No parameter schema on file.
Lists
No parameter schema on file.
Extracts plain text from one PDF, returning per-page text, the extractor
No parameter schema on file.
Runs Tesseract OCR over each page of an image-only/scanned PDF. Every page reports \
No parameter schema on file.
No parameter schema on file.
ML-embedding retrieval via @huggingface/transformers + paraphrase-multilingual-MiniLM-L12-v2 q8 (50+ languages, 384-dim, runs on CPU). Higher-quality than
No parameter schema on file.
v3.1.0 — HyDE retrieval (Gao et al 2023). Caller agent generates a synthetic answer to its own question, passes it as
No parameter schema on file.
The default search tool for v2.0. Auto-detects every available retrieval signal — BM25 via FTS5 (if
No parameter schema on file.
Parse a note
No parameter schema on file.
Given a question, retrieve the top relevant Markdown notes (via hybrid search), gather backlink summaries + optionally recent dailies, deduplicate, pack to a token budget, and return a single ready-to-paste markdown bundle. Ranked PDF hits are never parsed as Markdown: their paths are returned in
No parameter schema on file.
Return parsed YAML frontmatter for a note. With
No parameter schema on file.
Find every note where frontmatter.<key> matches a predicate. Useful as a precursor to bulk frontmatter_set:
No parameter schema on file.
Close the retrieval feedback loop: after using
No parameter schema on file.
Create a new note inside the vault. Refuses to overwrite unless overwrite=true. Frontmatter is rendered as YAML when supplied. WRITE TOOL — only available when the server is started with --enable-write.
No parameter schema on file.
Append a block of markdown to the end of an existing note. Provide either path or title. WRITE TOOL — only available when the server is started with --enable-write.
No parameter schema on file.
Atomically rename a note AND rewrite every [[wikilink]] / ![[embed]] in the rest of the vault that resolves to it — preserving |alias, #section, ^block, and the user
No parameter schema on file.
Walks the vault (or a
No parameter schema on file.
Convenience wrapper around obsidian_rename_note for the common archive workflow. Moves the note
No parameter schema on file.
Add a user/assistant/system message to a note
No parameter schema on file.
Surgical YAML manipulation: set one or more keys, or remove them by passing
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Enquire or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 3.11.6 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digesta0244f1f577430e41b6cc4fb1f77c1413b09e16d51efb3dae5fcb88154a10da8
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (46 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 46 recovered tools are registered only when diagnosticSearchTools holds (dist/tool-registry.js:183) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 43.
1 of the 46 recovered tools are registered only when diagnosticSearchTools holds (dist/tool-registry.js:655) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 43.
1 of the 46 recovered tools are registered only when diagnosticSearchTools holds (dist/tool-registry.js:680) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 43.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
43 tools are registered unconditionally · (1) 1 more only when diagnosticSearchTools holds (dist/tool-registry.js:183) · (2) 1 more only when diagnosticSearchTools holds (dist/tool-registry.js:655) · (3) 1 more only when diagnosticSearchTools holds (dist/tool-registry.js:680) — typically when a key or option is configured. All 46 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| obsidian_full_text_search | no tags | |
| obsidian_list_notes | no tags | |
| obsidian_read_note | no tags | |
| obsidian_resolve_wikilink | no tags | |
| obsidian_search_text conditional (1) | no tags | |
| obsidian_get_recent_edits | no tags | |
| obsidian_stale_notes | no tags | |
| obsidian_get_backlinks | no tags | |
| obsidian_list_tags | no tags | |
| obsidian_dataview_query | no tags | |
| obsidian_get_unresolved_wikilinks | no tags | |
| obsidian_get_outbound_links | no tags | |
| obsidian_validate_note_proposal | no tags | |
| obsidian_find_similar | no tags | |
| obsidian_get_note_neighbors | no tags | |
| obsidian_stats | no tags | |
| obsidian_lint_wiki | no tags | |
| obsidian_open_questions | no tags | |
| obsidian_paper_audit | no tags | |
| obsidian_find_path | no tags | |
| obsidian_open_in_ui | no tags | |
| obsidian_list_canvases | no tags | |
| obsidian_get_communities | no tags | |
| obsidian_list_bases | no tags | |
| obsidian_read_base | no tags | |
| obsidian_query_base | no tags | |
| obsidian_read_canvas | no tags | |
| obsidian_list_pdfs | no tags | |
| obsidian_read_pdf | no tags | |
| obsidian_ocr_pdf | no tags | |
| obsidian_semantic_search conditional (2) | untrusted-input | untrusted-input: keyword "download" |
| obsidian_embeddings_search conditional (3) | untrusted-input | untrusted-input: keyword "download" |
| obsidian_hyde_search | no tags | |
| obsidian_search | no tags | |
| obsidian_chat_thread_read | no tags | |
| obsidian_context_pack | no tags | |
| obsidian_frontmatter_get | no tags | |
| obsidian_frontmatter_search | no tags | |
| obsidian_mark_useful | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| obsidian_create_note | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| obsidian_append_to_note | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| obsidian_rename_note | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| obsidian_replace_in_notes | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| obsidian_archive_note | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| obsidian_chat_thread_append | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| obsidian_frontmatter_set | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digesta0244f1f577430e4
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 3.11.6. Pin a release below and the command asks for exactly that one.
3.11.6
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Enquire can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.