Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
Nothing to run from here
Web Intel 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
10
tools declared
remote
at its publisher
—
calls last 7d
What it does
8 pay-per-call web intel tools over MCP. Free discovery, calls settle in USDC on Base (x402).
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http timzinin-web-intel-mcp https://api.timzinin.com/mcp/web-intel
# 2 — ask your agent for something these tools do
# pricing_info, domain-health-checker, shopify-price-change-monitor and 7 more
Web Intel costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TIAll 12 servers
timzinin12 servers
5 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 timzinin-web-intel-mcp https://api.timzinin.com/mcp/web-intelReconnect, 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 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
10 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.
Free — list every paid tool in the 'web-intel' bundle with its price, payTo address and network. Call this first if you don't have a wallet ready yet.
No parameter schema on file.
Bulk-audit domains: DNS records, SSL certificate expiry, SPF & DMARC email authentication. Find domains that cannot receive email, are easy to spoof, or have expiring certificates — before your clients do. — $0.01/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domains | array | yes | List of domains to audit (e.g. example.com). |
| maxConcurrency | integer | no | How many domains to check in parallel. |
Watches a Shopify store's catalogue and returns only the products whose price or availability changed since the previous check. The first run creates the baseline and says so. — $0.05/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| websites | array | yes | Shopify (or possibly-Shopify) store URLs to watch, e.g. "allbirds.com". Every scheduled run re-checks these same sites and reports ONLY what changed since a previous run of this watch: a store newly a |
| baseline_key | string | no | A name for THIS watch, so you can run several independent store watches from one Actor (e.g. "dtc-competitors", "my-portfolio") without one overwriting another's memory of what's already been seen. Ea |
| max_items | integer | no | Caps how many new-store / changed-store rows a single run will deliver and charge for, even if more were found. |
Confirm a site runs on Shopify and pull store intelligence from its public feeds — product count, price range, top vendors/categories, newest listing and a rough revenue-band heuristic. No login, no Shopify API key. — $0.01/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| websites | array | yes | List of websites to check (e.g. allbirds.com or https://example.com). One row per site. |
| maxConcurrency | integer | no | How many websites to check in parallel. |
Give it a domain. It reads the sitemap, fetches the pages, strips them to clean text and splits everything into ~1000-char chunks — one dataset row per chunk, ready to embed into a vector store. No browser, no LLM, no API key. — $0.02/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| items | array | yes | List of domains or website URLs to crawl via their sitemap. One entry per site. |
| maxConcurrency | integer | no | How many SITES to process in parallel (each site already fetches up to 25 pages internally). |
Turn any URL into clean structured JSON — title, description, image, JSON-LD, headings, links, emails and prices — extracted deterministically via regex. Zero LLM calls, zero API keys. Built for AI agents that need one page turned into typed data, cheaply. — $0.01/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| urls | array | yes | List of URLs to extract structured data from. One row per URL. |
| fields | array | no | Optional subset of fields to return: title, description, image, siteName, canonical, jsonLd, headings, links, emails, prices. Leave empty to extract all of them. |
| maxConcurrency | integer | no | How many URLs to process in parallel. |
Detect a website's current technologies (CMS, ecommerce, analytics, marketing/CRM, framework, hosting/CDN, chat, payments) and diff it against a previously-seen stack you supply, so you get exactly what was added or removed. No browser, no proxies, no login. — $0.01/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| items | array | yes | One entry per domain. Bare form: "example.com" (just detects the current stack). Diff form: "example.com|Tech1,Tech2,Tech3" — everything after the pipe is the stack you last saw for this domain; the A |
| maxConcurrency | integer | no | How many domains to check in parallel. |
Detect the technologies a website runs — CMS, ecommerce platform, analytics, marketing/CRM, JS framework, hosting/CDN, chat and payments — straight from its public HTML and HTTP headers. No browser, no proxies, no login. Built for sales targeting and competitive research. — $0.01/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| websites | array | yes | List of websites to fingerprint (e.g. shopify.com or https://example.com). One row per site. |
| maxConcurrency | integer | no | How many websites to fingerprint in parallel. |
Fetch any URL and convert it into clean, LLM-ready Markdown — headings, links, lists and emphasis preserved, scripts/nav/ads stripped. No browser, no LLM calls, no API key. Built for RAG pipelines and AI agents that need one page turned into readable text, cheaply. — $0.01/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| urls | array | yes | List of URLs to fetch and convert to Markdown. One row per URL. |
| includeLinks | boolean | no | Convert <a href> tags to Markdown links. Turn off to strip links and keep only their text. |
| maxConcurrency | integer | no | How many URLs to fetch and convert in parallel. |
Pull live product catalogs (name, price, sale price, category, image) straight from Zid storefronts — a common Saudi/Gulf e-commerce SaaS — via their own public JSON feed. No login, no browser, no proxies. — $0.02/call, x402 (USDC on base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| items | array | yes | One entry per Zid storefront — the shop's subdomain (e.g. furniture) or full host (furniture.zid.store). Find the subdomain in the store's own zid.store URL, or via its custom domain's storefront |
| maxConcurrency | integer | no | How many shops to scan in parallel. |
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 Web Intel 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 1.0.0 · scanned 20 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 · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest2dcb98cca562d2b2f9cd205e6a92c04855a037940473032fa11dcc0bae63d515
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 |
|---|---|---|
| pricing_info | no tags | |
| domain-health-checker | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| shopify-price-change-monitor | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| shopify-store-intelligence | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sitemap-to-knowledge | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| structured-extract | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| tech-stack-change-detector | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| tech-stack-detector | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| url-to-markdown | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| zid-store-products | 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest2dcb98cca562d2b2
Scanned2026-10-20
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 1.0.0.
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 Web Intel 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.