Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
Nothing to run from here
Agent Data Tools: Web, documents and search 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
tool-list score
11
tools declared
remote
at its publisher
—
calls last 7d
What it does
24 tools: web pages, JS apps and PDFs as text, feeds, sitemaps, search. 25 free calls.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agent-data-tools-web-documents-and-search-mcp https://agent-data-tools.revmesh2074.workers.dev/mcp/web
# 2 — ask your agent for something these tools do
# extract, sitemap, summarize and 8 more
Agent Data Tools: Web, documents and search costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NUAll 8 servers
Nutshell20008 servers
7 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http agent-data-tools-web-documents-and-search-mcp https://agent-data-tools.revmesh2074.workers.dev/mcp/webReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take Authorization header (Optional. 'Bearer adt_...' API key from https://agent-data-tools.revmesh2074.workers.dev/credits to pay by card. Leave empty to pay each call with x402 (USDC).) if you want to set it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
11 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.
Fetch any public web page URL and get clean, LLM-ready text or Markdown: main content, code blocks, tables, links and headings, for RAG and agent context. Static HTML, Markdown or text; optional section ID. Default 20,000 output characters, max 100,000; input 2 MiB. No JavaScript rendering (see /extract/rendered), logins or paywalls. Empty pages, bad sections, browser challenges and errors are not
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute http(s) URL of the page to fetch |
| maxChars | integer | no | Maximum characters of body text to return (500-100000, default 20000) |
| format | string | no | Returned representation: text (default), markdown, or both. HTML structured details are included in every format; Markdown/plain sources have empty details. |
| section | string | no | Optional exact visible HTML ID within primary content, 1-500 characters. Heading scope includes subsections until next same/higher-level heading; section/article/main/div scope is its subtree. Missing |
Read one public XML sitemap or sitemap index as structured URLs and source-reported dates. Supports gzip, substring filtering and pagination. Maximum 512 KiB expanded input and 1000 entries. Does not crawl pages or follow child sitemaps. Invalid XML and execution errors are not charged; a valid empty match is charged. Use to find which pages of a docs site to read before calling /extract. Example:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute public HTTP(S) XML sitemap URL; child sitemaps are not fetched automatically |
| contains | string | no | Optional case-insensitive URL substring, at most 200 characters |
| maxUrls | integer | no | Reported matching locations examined in one page (1-100, default 25); invalid/nonpublic locations may reduce returned entries |
| offset | integer | no | Offset into distinct reported matching locations (0-1000, default 0); use nextOffset to continue |
Give a URL, get a short summary of the page plus three to six key points, ready to drop into an agent's context. Fetches the page, strips navigation and boilerplate, and summarizes the main text with an LLM. HTML pages only; for a PDF use pdf_text, then ai_summarize_text. Use for research, news triage, link previews and deciding whether a page is worth reading in full. Example: url=https://en.wiki
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute http(s) URL of the page to summarize |
Render any public web page in a real headless Chrome browser, with JavaScript executed, and get a JPEG screenshot (1280 px wide, base64) plus the final URL, HTTP status and page title. Set fullPage=true to capture up to 4000 px of page height. Use for visual checks, page previews, monitoring and feeding pages to vision models. Example: url=https://example.com. Price $0.02/call via x402 USDC or a c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute http(s) URL of the page to capture |
| fullPage | string/number/boolean | no | Set to true to capture the full page height (max 4000 px) instead of the 1280x800 viewport |
Search scholarly literature across journals, conferences, preprints and books: title, authors, year, venue, citation count, DOI link and abstract where available. Optional fromYear filter and up to 20 results per call. Use for research agents, literature reviews, fact-checking a claim against published work, and finding the DOI for a citation. Example: query=CRISPR off-target effects. Price $0.003
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search terms, a title or a research question (3-300 characters) |
| limit | integer | no | Number of results, 1-20 (default 5) |
| fromYear | integer | no | Only works published in or after this year |
Download a public PDF (up to 10 MB) and return its text page by page, with title, author, page count and character counts. Choose a first page and how many pages to read (up to 200) and cap the output with maxChars. Scanned PDFs without a text layer, encrypted files and non-PDF URLs fail uncharged. Use to read papers, invoices, reports and manuals into an agent's context. Example: url=https://bitc
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute public http(s) URL of the PDF |
| firstPage | integer | no | First page to read (default 1) |
| pages | integer | no | How many pages to read (1-200, default 50) |
| maxChars | integer | no | Maximum characters of text returned across all pages (1000-200000, default 50000) |
Same output as /extract, but the page is first rendered in a real browser, so single-page apps and pages that build their content with JavaScript come back with their text instead of an empty shell. Waits for the network to settle (up to 15 seconds). Public pages only; no login. Use when /extract returns EXTRACTION_EMPTY or too little text for a page you can read in a browser. Example: url=https:/
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute public http(s) URL of the page |
| format | string | no | text (default), markdown or both |
| maxChars | integer | no | Output limit, 500-100000 characters (default 20000) |
| section | string | no | Optional exact HTML id to read only that element |
Read a public RSS 2.0, RSS 1.0 or Atom feed and get the feed title, link and description plus its newest items: title, link, date (ISO 8601), short plain-text summary, author and id. Up to 50 items, feeds up to 2 MB. Lenient with real-world feeds; a page that is not a feed returns 422, uncharged. Use to follow news, blogs, release notes or podcasts without scraping pages. Example: url=https://gith
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute public http(s) URL of the feed |
| limit | integer | no | Items to return (1-50, default 20) |
Fetch a public web page's head and return link-preview metadata: title, description, site name, type, preview image, canonical URL, language, author, published time, favicon, theme colour, and every OpenGraph and Twitter-card field. Reads at most 512 KB and never runs JavaScript. Use to build link previews, label citations or check how a URL will unfurl before sharing it. Example: url=https://gith
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Absolute public http(s) URL of the page |
Short summary of a Wikipedia article in any language edition: title, one-paragraph extract, description, thumbnail and page URL. Use to ground an agent's answer in a quick, citable fact sheet. Example: title=Stockholm. Price $0.003/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | Article title |
| lang | string | no | Language code (default en) |
Definitions of an English word from Wiktionary, grouped by part of speech, with example sentences where Wiktionary gives them, plus the page link and the CC BY-SA attribution to show. Use for writing help, vocabulary, translation checks and word games. Example: word=serendipity. Price $0.003/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| word | string | yes | An English word |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Agent Data Tools: Web, documents and search 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: —
ATool-list grade · score 93 / 100
Release 1.82.18 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
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
Findings0 threat · 8 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest8d69e28f643deb54d115821477f2e49dbc1745a92cca86103e186ccb2a937b66
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| extract | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| sitemap | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| summarize | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| screenshot | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| papers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| pdf_text | untrusted-input | untrusted-input: keyword "download", declares openWorldHint: true (interacts with entities outside the server) |
| extract_rendered | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| feed | untrusted-input | untrusted-input: keyword "rss", declares openWorldHint: true (interacts with entities outside the server) |
| url_meta | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| wikipedia | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| dictionary | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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 digest8d69e28f643deb54
Scanned2026-10-28
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.82.18.
1.82.18
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 Agent Data Tools: Web, documents and search 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.