Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Everkeep 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.
What it does
Your notes in one folder on your own server; AI clients read and edit it under write policies
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'EVERKEEP_VAULT=${EVERKEEP_VAULT}' --transport stdio everkeep-mcp '--' npx -y everkeep
# 2 — ask your agent for something these tools do
# grep_files, read_text_file, read_file and 17 more
It needs EVERKEEP_VAULT: this reads it from your environment, so export it first.
Everkeep costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Everkeep as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads EVERKEEP_VAULT (Absolute path of the folder the server reads and edits (the vault)) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx EVERKEEP_VAULT … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'EVERKEEP_VAULT=${EVERKEEP_VAULT}' --transport stdio everkeep-mcp '--' npx -y everkeepReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs settings only you can give it: EVERKEEP_VAULT — Absolute path of the folder the server reads and edits (the vault). You set it in your own client’s config, on your machine — this marketplace never holds it.
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.
20 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.
Search file CONTENTS by regex, recursively. Per file returns path, rev, line count, then matching line numbers with their text. Long lines are clipped around the match (max_line_length, default 200). Line numbers and rev feed straight into read_text_file offset/limit and edit_file line edits.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | File or directory (recursive) |
| pattern | string | yes | JavaScript regex |
| ignore_case | boolean | no | — |
| include | string | no | Filename glob, comma-separated: "*.md,*.yaml" |
| exclude | string | no | Glob to skip |
| context | number | no | ±N lines around each match (default 0) |
| max_results | number | no | Default 50 |
| max_line_length | number | no | Default 200 |
| documents | boolean | no | false skips documents. Default true |
Read one file. Whole file by default; head/tail = N lines from an edge; offset/limit = an arbitrary 1-based line range, which also reports total lines and rev (needed for edit_file line edits). Documents (PDF, DOCX, XLSX, PPTX, ODF, EPUB, MSG…) come as numbered lines with section markers, no rev,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| head | number | no | — |
| tail | number | no | — |
| offset | number | no | First line, 1-based |
| limit | number | no | Number of lines from offset |
| extract | boolean | no | HTML/RTF/EML/FB2: their text instead of the raw file |
DEPRECATED alias of read_text_file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| head | number | no | — |
| tail | number | no | — |
| offset | number | no | — |
| limit | number | no | — |
Read an image, audio or PDF file. PDF returns one page (default 1, or "#N" path suffix) as JPEG plus the total page count. For PDF text use read_pdf_text; one PDF page as an image: read_pdf_page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
Render one PDF page (1-based) as JPEG. Prefer read_pdf_text unless layout or graphics matter.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| page | number | yes | — |
Text of a PDF, whole or a page range, as numbered lines with page markers (the same numbers as read_text_file). Much cheaper than page images — prefer it; for scans use read_pdf_page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| first_page | number | no | — |
| last_page | number | no | — |
Inspect a SQLite database file: schema-neutral, no interpretation of the data. File type is decided by the first 16 bytes, not the extension. Returns table/index/view/trigger DDL from sqlite_master, the journal_mode/page_size/page_count/encoding/user_version/application_id PRAGMAs, the sqlite3…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| counts | boolean | no | Add COUNT(*) per table (full table scan each). Default false. |
| counts_timeout_ms | number | no | Per-table budget (covers spawning sqlite3 + opening the file + the COUNT), not a pool shared across tables. Default 60000, max 600000. |
Run one read-only SQL statement on a SQLite file (sqlite3 -readonly -safe -json; ATTACH and other escapes are disabled). Must start with SELECT, WITH, VALUES, or EXPLAIN [QUERY PLAN] followed by one of those. Runs wrapped as SELECT * FROM (<sql>) LIMIT <limit+1>; truncated=true means more rows…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| sql | string | yes | — |
| limit | number | no | Default 100, max 1000. |
| timeout_ms | number | no | Default 5000, max 30000. |
Read several whole files at once (documents as numbered lines, as read_text_file; the trash is skipped). For a line range or rev use read_text_file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | array | yes | — |
Create or overwrite a file with given content. In a zone with policy overwrite="rev", overwriting an EXISTING file requires its current rev (creating a new one does not); the refusal message carries the rev to use. For a change inside a file use edit_file. Document formats (PDF, DOCX…) are not…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| content | string | yes | — |
| rev | string | no | Current rev of the file being overwritten. From grep_files, read_text_file offset, or get_file_info. |
Edit a file. Two mutually exclusive edit shapes: {oldText,newText} literal replacement, or line edits (1-based). {startLine,endLine,newText} replaces the inclusive range; newText "" deletes, no trailing newline. Omitting endLine INSERTS before startLine instead of replacing, and startLine =…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| edits | array | yes | — |
| rev | string | no | From grep_files, read_text_file offset, or get_file_info |
| dryRun | boolean | no | — |
Create a directory (and parents); an existing one is not an error. Refused where the zone policy forbids writing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
List one directory; the first line is the policy in force. Sizes: list_directory_with_sizes; deeper levels: directory_tree.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
List a directory with file sizes, sorted by name or size. Without sizes: list_directory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| sortBy | string | no | — |
Recursive tree view, 2 levels deep. One level: list_directory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
Move or rename a file or directory. Taking a file out of a zone with policy overwrite="rev" requires its current rev, exactly like overwriting it in place; directories are not moved out of a strict zone at all. Use trash_file, not this, to discard something; moving a file out of the trash restores…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | — |
| destination | string | yes | — |
| rev | string | no | Current rev of the source file, required when it leaves a zone with overwrite="rev". |
Discard a file by moving it into the trash of its own zone, keeping its relative path and adding an arrival timestamp to the name. There is no delete: this is the only way to remove something. Fails if the zone has no trash configured. In a zone with overwrite="rev" the current rev is required —…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| rev | string | no | Current rev of the file, required in a zone with overwrite="rev". |
Find files by NAME substring, recursively. For content use grep_files.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| pattern | string | yes | — |
| excludePatterns | array | no | — |
Metadata for a file or directory: size, times, format, plus line count and rev for text files (the rev that writes in a strict zone ask for). Content: read_text_file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
The vault root; every path must be inside it. Start here if the vault path is unknown.
No parameter schema on file.
- 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 Everkeep or to call it, at any volume.
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.
| 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 |
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.
Tools were statically extracted from the published source (20 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>".
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 |
|---|---|---|
| grep_files | no tags | |
| read_text_file | no tags | |
| read_file | sensitive-source | sensitive-source: keyword "read_file" |
| read_media_file | no tags | |
| read_pdf_page | no tags | |
| read_pdf_text | no tags | |
| sqlite_schema | no tags | |
| sqlite_query | sensitive-source | sensitive-source: parameter "sql" |
| read_multiple_files | no tags | |
| write_file | file-write | file-write: keyword "write_file" in tool name |
| edit_file | file-write | file-write: keyword "edit_file" in tool name |
| create_directory | no tags | |
| list_directory | no tags | |
| list_directory_with_sizes | no tags | |
| directory_tree | no tags | |
| move_file | file-write | file-write: keyword "move_file" in tool name |
| trash_file | no tags | |
| search_files | no tags | |
| get_file_info | no tags | |
| list_allowed_directories | no tags |
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
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 1.0.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
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.
Any signed-in account that does not publish Everkeep can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.