MCP server for advanced web search using Tavily
Nothing to run from here
Agentutility Web Probe 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.
99/100
trust score
17
downloads a day
local
runs on your machine
631
downloads in 30d
What it does
MCP server for the @agentutility web-probe cluster — pay-per-call x402 tools, no API keys, USDC on Base.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user agentutility-web-probe-mcp '--' npx -y @agentutility/mcp-web-probe
# 2 — ask your agent for something these tools do
# archive-snapshot-api, archive-url, arxiv-search and 58 more
Agentutility Web Probe costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AGAll 20 servers
@agentutility20 servers
13 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 Agentutility Web Probe 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.
Claude Codedeclared by this listing
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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user agentutility-web-probe-mcp '--' npx -y @agentutility/mcp-web-probeReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: 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 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.
What you approve
61 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.
(0.02 USDC/call) Finds archived snapshots of public web pages, returning the closest Wayback Machine captures with timestamps, status codes, and replay URLs. Same archive-snapshot backend. Use it as an archive snapshot API, Wayback Machine snapshot lookup, or historical URL capture source.
No parameter schema on file.
(0.02 USDC/call) Looks up the archived copy of a public URL closest to a given timestamp and can fetch cleaned archived page text. Useful for citation repair, provenance checks, and reference rot fixes. Use it as an archive snapshot finder, web archive URL builder, or Wayback Machine snapshot API.
No parameter schema on file.
(0.03 USDC/call) Search arXiv
No parameter schema on file.
(0.04 USDC/call) Turn an arXiv paper into a structured research summary without reading the PDF. Send an arxiv_id_or_url (like \
No parameter schema on file.
(0.005 USDC/call) Checks whether a brand or company domain is established, expiring, registrar-locked, or newly registered, on the same RDAP backend as whois-lookup. Use it as a brand domain check API, startup domain diligence, or company-name domain screen.
No parameter schema on file.
(0.05 USDC/call) Generates brand name candidates and returns ranked names, slugs, rationale, checked TLDs, and availability counts. Same backend as domain-suggest, with exact brand-name wording for discovery. Use it as a product naming API or brandable domain suggester.
No parameter schema on file.
(0.005 USDC/call) Checks new or suspicious brand-adjacent domains for age, registrar, expiry, DNSSEC, and transfer/lock statuses. An unregistered lookalike domain answers with found:false instead of erroring — that
No parameter schema on file.
(0.03 USDC/call) Loads a public URL in a real headless browser with JavaScript executed, then returns the rendered HTML and page title, or a base64 screenshot. For pages a plain HTTP fetch can
No parameter schema on file.
(0.01 USDC/call) Enrich a company from its domain or an email address. Returns the normalized domain, inferred company name, MX records, and public homepage metadata (title, description, image, HTTP status). Public-data-only company/organization enrichment — no private databases or social scraping.
No parameter schema on file.
(0.005 USDC/call) Scores the quality of a company name before you commit to domain, handle, trademark, and launch work. Same backend as brand-name-score. Use it as a company name score API, business name evaluator, or startup name quality check.
No parameter schema on file.
(0.005 USDC/call) Checks creator, newsletter, podcast, and community domains for age, expiry, registrar, DNSSEC, and suspicious new-registration flags. Same RDAP backend as whois-lookup. Use it as a creator domain check API, newsletter domain age lookup, or personal brand domain diligence tool.
No parameter schema on file.
(0.005 USDC/call) Detects disposable and throwaway email addresses before they get through your signup form. Checks the email
No parameter schema on file.
(0.02 USDC/call) Audits a domain
No parameter schema on file.
(0.02 USDC/call) Checks a domain
No parameter schema on file.
(0.02 USDC/call) Checks a domain
No parameter schema on file.
(0.05 USDC/call) Generates domain name ideas: brainstorms domain-friendly names from a concept and checks RDAP availability across allowed TLDs. Same backend as domain-suggest. Use it as an available-domain-ideas generator or startup domain finder.
No parameter schema on file.
(0.005 USDC/call) Audits individual portfolio domains for age, expiry, registrar, DNSSEC, nameservers, and lock status before renewal or acquisition decisions. Same RDAP backend as whois-lookup. Use it as a domain portfolio risk API, registrar and expiry audit, or brand-domain inventory check.
No parameter schema on file.
(0.005 USDC/call) Monitors a domain
No parameter schema on file.
(0.02 USDC/call) Screens a domain for risk signals: age, expiration, registrar, nameservers, DNSSEC, status codes, and flags such as newly-registered or expiring-soon. Same backend as whois-lookup. Use it as a domain risk check API, phishing triage tool, or brand-protection domain screen.
No parameter schema on file.
(0.005 USDC/call) Scores an email domain
No parameter schema on file.
(0.005 USDC/call) Checks whether a sender or lead email domain is established, expiring, DNSSEC-signed, or newly registered. Same RDAP backend as whois-lookup. Use it as an email domain age check API, sender-domain diligence tool, or cold-email risk screen.
No parameter schema on file.
(0.005 USDC/call) Validates an email address and scores whether its domain can receive mail, reporting authentication records and disposable-domain risk without contacting the mailbox. Use it as an email domain health API, MX SPF DMARC DKIM checker, or mail authentication posture audit.
No parameter schema on file.
(0.005 USDC/call) Validates email syntax and domain health, returning a deliverability score, risk bucket, MX records, disposable-domain match, role-account signal, and SPF/DMARC/DKIM posture. Use it as an email validator, MX record checker, disposable email checker, or domain email health API.
No parameter schema on file.
(0.005 USDC/call) Equities news API (alias of stocks-news). Recent GDELT-backed headlines with a GNews fallback when configured on equities, earnings, IPOs, the Fed, and macro with sentiment and source domains. Data-only; no trading advice or price prediction.
No parameter schema on file.
(0.015 USDC/call) Grant lookup and federal funding opportunities search for agents scouting money on the table for nonprofits, small businesses, researchers, and local governments. Searches grants.gov
No parameter schema on file.
(0.03 USDC/call) Renders a URL with JavaScript enabled and returns the browser-rendered HTML, title, resolved URL, and truncation metadata, or captures a screenshot when screenshot=true. Use it as a JavaScript render API, JS page renderer, or single-page-app HTML renderer.
No parameter schema on file.
(0.002 USDC/call) Keyword and autocomplete suggestions for any seed query. Aggregates Wikipedia OpenSearch and DuckDuckGo autocomplete (both public, no auth) into a de-duplicated ranked list — useful for SEO keyword research, content-gap analysis, LLM query expansion, and agent-driven research.
No parameter schema on file.
(0.005 USDC/call) Extracts every link from a webpage: fetches the HTML URL and returns each <a> link with its anchor text, rel attribute, and an is_external flag. Resolves relative URLs against the page
No parameter schema on file.
(0.005 USDC/call) Runs M&A domain diligence, giving deal, finance, and procurement agents domain age, expiry, registrar, DNSSEC, nameserver, and transfer signals. Same whois-lookup backend. Use it as an M&A domain diligence API, acquisition domain history check, or company website RDAP check.
No parameter schema on file.
(0.005 USDC/call) Scores product name quality for agents naming products, features, apps, tools, newsletters, and APIs. Same backend as brand-name-score. Use it as a product name score API, product naming evaluator, or feature name quality check.
No parameter schema on file.
(0.005 USDC/call) Reads one or more QR codes from a public PNG, JPG, GIF, BMP, or SVG-rendered image URL and returns the decoded text strings. Use it as a QR code reader, QR code decode API, or scan-QR-from-image tool.
No parameter schema on file.
(0.005 USDC/call) Decodes QR codes, reading one or more codes from public PNG, JPG, GIF, BMP, or SVG-rendered image URLs. Same QR decode backend as qr-code. Use it as a QR code API, QR scanner API, or decode QR image endpoint.
No parameter schema on file.
(0.005 USDC/call) Reads QR codes out of any public image URL (PNG / JPG / GIF / BMP) and returns the decoded text strings. Multiple QR codes in a single image are returned as separate entries. Returns an empty
No parameter schema on file.
(0.001 USDC/call) Generates PNG or SVG QR codes from text, URLs, vCards, WiFi strings, and plain text with configurable size, margin, colors, and error correction. Use it as a QR generator API, create-QR-code endpoint, text-to-QR, or link QR generator.
No parameter schema on file.
(0.005 USDC/call) Scans a public image URL for QR codes and returns each one
No parameter schema on file.
(0.02 USDC/call) Finds a domain
No parameter schema on file.
(0.005 USDC/call) Fetches and parses a site
No parameter schema on file.
(0.005 USDC/call) Checks whether a proposed X/Twitter handle is claimed and returns public account metrics when it exists. Same read-only X API backend as x-handle-availability. Use it as a social handle check, X username availability lookup, or startup brand handle lookup.
No parameter schema on file.
(0.03 USDC/call) Checks a domain
No parameter schema on file.
(0.03 USDC/call) Inspects a domain
No parameter schema on file.
(0.03 USDC/call) Check a domain
No parameter schema on file.
(0.005 USDC/call) Checks a domain
No parameter schema on file.
(0.05 USDC/call) Generates candidate names for a startup concept and checks matching domain availability across common startup TLDs. Same backend as domain-suggest. Use it as a startup name generator, product name generator, or founder naming API.
No parameter schema on file.
(0.005 USDC/call) Stock news / equities headlines (alias of stocks-news). GDELT-backed public news with a GNews fallback when configured on stocks, earnings, IPOs, the Fed, and macro with sentiment. Buyer-wording variant of stocks-news. Data-only; no trading advice.
No parameter schema on file.
(0.03 USDC/call) Enumerates a domain
No parameter schema on file.
(0.01 USDC/call) Looks up tweets by ID and returns public text, timestamps, metrics, language, and expanded author profiles. Same read-only X API v2 backend as tweets; accepts tweet_ids or ids. No account mutation. Use it as a tweet lookup API, X tweet lookup, or Twitter status lookup by ID.
No parameter schema on file.
(0.006 USDC/call) Searches recent public X posts with author expansion and public metrics. Same backend as x-search, with exact tweet-search buyer wording; read-only X API v2 recent search. Use it as a tweet search API, Twitter recent search, or X public post search.
No parameter schema on file.
(0.01 USDC/call) Returns recent public tweets by username, using the same read-only X API v2 user_tweets backend as user-tweets. Exposed under the buyer wording used by /tweets/user-style clients. Use it as a tweets-by-username or Twitter user timeline API.
No parameter schema on file.
(0.005 USDC/call) Resolves a Twitter or X username to a public profile with a read-only X API v2 lookup; no account mutation. Same backend as x-username, under broad buyer wording. Use it as a Twitter user lookup or public profile resolver.
No parameter schema on file.
(0.01 USDC/call) Looks up a Twitter user
No parameter schema on file.
(0.01 USDC/call) Looks up Twitter user profiles in bulk by username or ID, for routers and buyers searching for bulk profile enrichment. Same backend as users. Use it as a Twitter users API or bulk user profile lookup by username or ID.
No parameter schema on file.
(0.01 USDC/call) Read-only X API v2 wrapper for tweet search, tweet lookup, username lookup, bulk users lookup, and user timeline fetch. Set mode=
No parameter schema on file.
(0.02 USDC/call) Expands shortened URLs from bit.ly, t.co, lnkd.in, goo.gl, tinyurl, and other redirects into final landing URLs, with hop-by-hop status, Location, content-type, and timing details. Same expand-url backend. Use it as a URL expander API, shortlink resolver, or redirect-chain tracer.
No parameter schema on file.
(0.01 USDC/call) Fetches the latest public tweets from any X username, with text, timestamps, metrics, pagination token, and author profile. Read-only X API v2 route: resolves a public username, fetches that user
No parameter schema on file.
(0.005 USDC/call) Screens vendor domains for age, expiration, registrar, DNSSEC, nameservers, and suspicious newly-registered risk flags. Same RDAP backend as whois-lookup. Use it as a vendor domain risk API, supplier website age check, or procurement domain diligence tool.
No parameter schema on file.
(0.01 USDC/call) Monitors a webpage for changes and remembers the state server-side: caller picks a watch_id and the server stores the page
No parameter schema on file.
(0.02 USDC/call) Finds the closest archived URL for a public page and optional timestamp, with cleaned archived text for citation repair. Use it as a Wayback lookup, archive snapshot API, or historical page capture finder.
No parameter schema on file.
(0.02 USDC/call) Finds Wayback Machine captures of a page by URL and timestamp, and can fetch cleaned archived text. Use it as an archive.org snapshot lookup, historical URL capture finder, or archived page text fetcher.
No parameter schema on file.
(0.02 USDC/call) Returns the closest archived snapshot URL and timestamp for a public web page, with optional cleaned text fetch for reference rot repair and due-diligence citations. Use it as a web archive lookup, archive snapshot API, Wayback Machine API, or historical webpage snapshot.
No parameter schema on file.
(0.005 USDC/call) WHOIS API and RDAP domain lookup for agents. Returns registration date, domain age, expiration date, registrar, contacts, nameservers, DNSSEC status, EPP status codes, transfer history, and risk flags from the IANA-mandated RDAP endpoint for the domain
No parameter schema on file.
(0.01 USDC/call) Fetches public X profiles and metric fields in bulk from usernames or numeric user IDs. Same read-only X API v2 backend as users. Use it as an X users API, bulk Twitter profile lookup, or public social profile lookup.
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 Agentutility Web Probe 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 99 / 100
Release 0.32.19 · scanned 14 Oct 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 score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest5af0667d4445d8634a638e08e16f37928e90f2165ee211246e2765a5683df266
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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. minimal 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. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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 digest5af0667d4445d863
Scanned2026-10-14
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.32.19. Pin a release below and the command asks for exactly that one.
0.32.19
undated
latest- 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.
0.32.1
undated
- The version the registry reports for this listing; it was 0.17.5.
0.17.5
9 Aug 2026
No 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 Agentutility Web Probe 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.