Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
Cairn 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.
93/100
trust score
16
tools declared
local
runs on your machine
—
calls last 7d
What it does
Second brain as plain Markdown in your repo: search, notes, capture, journal, task queue.
Quickstart
Install it the way its author documents:
1. Download cairn.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is bac2780f3c5fadd4955f62f7594e9adf37b3a9a8445acd3e9b3a6cad182d5219
The full guide: https://github.com/juw12/cairn/releases/download/mcp-v1.0.0/cairn.mcpb
Publishernot claimed
JUAll 2 servers
juw122 servers
2 categories
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 Cairn 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.
Install it the way its author documents:
1. Download cairn.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is bac2780f3c5fadd4955f62f7594e9adf37b3a9a8445acd3e9b3a6cad182d5219
The full guide: https://github.com/juw12/cairn/releases/download/mcp-v1.0.0/cairn.mcpb
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Search ideas, tasks, decisions, notes and journal pages. Every word must match; titles and tags rank first. Use it before answering 'why did we...' questions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Words to find, #tags allowed |
| type | string | no | Only this kind of note |
| limit | integer | no | — |
Read one note in full (frontmatter and Markdown body) plus the notes that link to it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | yes | — |
List notes, optionally filtered by type, status (e.g. task todo/doing/done, decision accepted) or tag.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | — |
| status | string | no | — |
| tag | string | no | — |
| limit | integer | no | — |
One-page project brief: goals, open tasks, accepted decisions, active ideas and the latest journal lines. Read this first.
No parameter schema on file.
What happened lately: journal entries of the last N days and the most recently changed notes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | — |
TODO, FIXME and HACK comments found in the repo's code, with file:line.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
Create a note from one line. Prefix picks the kind: 'idea:', 'todo:', 'decision:', 'note:', 'feedback:'; #tags become tags. Example: 'decision: cache in SQLite, not Redis #storage'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Prefix, title and #tags on one line |
| body | string | no | Optional Markdown body (for a decision: context, options, decision, consequences) |
Change a note in place: set its status (task todo/doing/done, idea raw/exploring/ready/parked, decision proposed/accepted/superseded), add or remove tags, or append Markdown. Other fields are kept as they are.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | yes | — | |
| status | string | no | — |
| add_tags | array | no | — |
| remove_tags | array | no | — |
| append | string | no | Markdown added at the end of the body |
Add a timestamped line to today's journal page. 'todo:'/'idea:'/'decision:' lines also create that note and link it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Before starting a delegated goal: a brief built from the user's own history. Draft Definition of Done, hidden asks (what they asked for next after similar goals), closest past prompts, lessons, related notes, their working profile, the queue and the work loop.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | no | The goal in the user's words; empty takes the top queue item |
| k | integer | no | — |
The next open item of the work queue (tasks tagged #queue), skipping items blocked on the user (#needs-me).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| auto_only | boolean | no | Only items marked safe to run unattended (#auto) |
Add a follow-up to the work queue instead of asking the user. auto: safe to run unattended; needs_me: blocked until the user acts (a login, a purchase, a decision only they can make).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| auto | boolean | no | — |
| needs_me | boolean | no | — |
When a goal is done: record what was delivered and any correction the user made, so the next brief learns from it. queue_path also marks that queue task done.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | — |
| delivered | string | yes | — |
| correction | string | no | — |
| queue_path | no | — |
Open tasks, accepted decisions, active ideas and the recent log, as context for this chat.
No parameter schema on file.
Hand over a goal: the brief from your own precedents plus the loop to build, verify, publish and log it without check-ins.
No parameter schema on file.
What you want done; empty takes the top queue item
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 Cairn 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 93 / 100
Release 1.0.0 · scanned 14 Nov 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 score93
Findings11 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
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 digest2dc22d3bf39daa39
Scanned2026-11-14
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
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 1.0.0.
1.0.0
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 Cairn 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.