MCP server for advanced web search using Tavily
Nothing to run from here
RootMind 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
5
tools declared
local
runs on your machine
254
downloads
What it does
RootMind indexes the folders you choose on your own computer and lets Claude Desktop, Claude Code, n8n or any MCP client search them. Your documents never leave your machine; only the passages the assistant reads go to the model you use.
Tools
- search_documents: full-text search (SQLite FTS5) with phrases, word prefixes, file type and folder filters. Results come with the file name, page or sheet, and a snippet.
- search_fuzzy: finds names and terms with typos or other spellings
- list_documents: lists files by name, type or folder
- read_document: reads a document or a page range, so answers can quote the exact page
- get_statistics: what is indexed and how much
Why it’s different
- No embeddings, no vector database: exact matches, also in very large documents (tested on 18,000+ files, 2 billion characters)
- Answers cite file and page, so you can check them
- Runs as a background service on Windows and Linux. The MCP server needs a bearer token and listens on 127.0.0.1 only.
Needs: the free RootMind app (Windows or Linux) with “Serve MCP over HTTP” on, which is the default.
Quickstart
Install it the way its author documents:
1. Install the RootMind app for Windows or Linux, with "Serve MCP over HTTP" on (the default): https://github.com/cgaeking/rootmind/releases/latest
2. Download https://github.com/cgaeking/rootmind/releases/latest/download/rootmind.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
3. Optional: check the download against https://github.com/cgaeking/rootmind/releases/latest/download/SHA256SUMS.txt
The full guide: https://github.com/cgaeking/rootmind#install
Publisher
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 RootMind 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. Install the RootMind app for Windows or Linux, with "Serve MCP over HTTP" on (the default): https://github.com/cgaeking/rootmind/releases/latest
2. Download https://github.com/cgaeking/rootmind/releases/latest/download/rootmind.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
3. Optional: check the download against https://github.com/cgaeking/rootmind/releases/latest/download/SHA256SUMS.txt
The full guide: https://github.com/cgaeking/rootmind#install
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search the user's own files on this computer (the local folders indexed by RootMind). Fast full-text search (SQLite FTS5) over all indexed documents. Matches exact words and word prefixes. USE THIS FIRST: it is fast and cheap. Returns matching documents with text snippets, the location (page/slide/sheet) when known, and a suggested read_document call around each hit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search term(s). Matches exact words and prefixes (e.g. 'invoice' also finds 'invoices'). |
| file_type | string | no | Optional: filter by file type, e.g. pdf, docx, xlsx, pptx, md, txt, csv |
| limit | integer | no | Maximum number of results (1-50, default 10). |
Trigram-based fuzzy search that tolerates typos. USE THIS ONLY when search_documents finds nothing or the search term may be misspelled (e.g. 'lantren' finds 'lantern').
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search term, typos allowed. Finds similar words. |
| file_type | string | no | Optional: filter by file type, e.g. pdf, docx, xlsx, pptx, md, txt, csv |
| min_similarity | number | no | Minimum similarity 0.1-1.0 (default 0.3). Higher means fewer but closer matches. |
| limit | integer | no | Maximum number of results (1-50, default 10). |
Read the text of a document, or a character window of it. At most 50,000 characters are returned per call; for large documents read the window around a known hit instead of paging through everything.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_id | string | yes | Document ID (from search_documents or list_documents). |
| start_char | integer | no | Optional: start position (character offset, default 0). |
| end_char | integer | no | Optional: end position (exclusive). Capped at start_char + 50,000. |
List indexed documents with metadata (no content). Use it for an overview of the available files or to find a file by name.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_type | string | no | Optional: filter by file type, e.g. pdf, docx, xlsx, pptx, md, txt, csv |
| search_filename | string | no | Optional: substring to look for in file names. |
| limit | integer | no | Maximum number of documents (1-200, default 50). |
Show statistics about the document collection (number of documents, file types, total size).
Takes no parameters.
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 RootMind 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 2.8.0 · scanned 2 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
Scanned2026-11-02
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 2.8.0.
2.8.0
2 Nov 2026
latestNo release note was published with this version.
2.7.0
1 Nov 2026
No release note was published with this version.
2.6.1
31 Oct 2026
No release note was published with this version.
2.6.0
30 Oct 2026
No release note was published with this version.
2.5.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 RootMind 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.