Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
Nothing to run from here
adhistory: Google Ads, reviews, jobs, PDFs 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.
96/100
trust score
75
downloads a day
local
runs on your machine
13
tools declared
What it does
Competitor Google ads, app reviews, job boards, PDF tables/invoices, email checks via Apify
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'APIFY_TOKEN=${APIFY_TOKEN}' --transport stdio adhistory-google-ads-reviews-jobs-pdfs-mcp '--' uvx adhistory-mcp
# 2 — ask your agent for something these tools do
# competitor_google_ads, app_reviews, workday_jobs and 10 more
It needs APIFY_TOKEN: this reads it from your environment, so export it first.
adhistory: Google Ads, reviews, jobs, PDFs costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
OBAll 1 server
obrandon1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts adhistory: Google Ads, reviews, jobs, PDFs as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads APIFY_TOKEN (Your Apify API token (free account): console.apify.com -> Settings -> API & Integrations) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx APIFY_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'APIFY_TOKEN=${APIFY_TOKEN}' --transport stdio adhistory-google-ads-reviews-jobs-pdfs-mcp '--' uvx adhistory-mcpReconnect, 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 asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: APIFY_TOKEN — Your Apify API token (free account): console.apify.com -> Settings -> API & Integrations. You set it in your own client’s config, on your machine — this marketplace never holds it.
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
13 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Get the ads a company or domain runs on Google (Search, YouTube, Shopping, Maps, Play, Display), read from the public Google Ads Transparency Center. Each item is one ad: advertiser name, format (text/image/video), headline and description for text ads, first and last shown dates, days running,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domains | array | no | Advertiser websites, e.g. ['hubspot.com']. URLs are fine. |
| company_names | array | no | Company names to look up in the Transparency Center; the best match is used. |
| advertiser_ids | array | no | Transparency Center advertiser IDs (start with AR). |
| mode | string | no | 'ads' lists ads; 'advertiserCheck' returns one summary row per domain. |
| max_ads_per_advertiser | integer | no | Newest ads first. Raise to reach older long-running ads. |
| country | no | Only ads shown in this country. ANY = all countries. | |
| platform | string | no | Only ads shown on this Google platform. |
| ad_format | string | no | text = Google Search ads; image and video cover Display and YouTube. |
| only_active_ads | boolean | no | Keep only ads shown in the last 3 days. |
| date_from | string | no | Optional start date, YYYY-MM-DD. |
| date_to | string | no | Optional end date, YYYY-MM-DD. |
Get user reviews for iOS App Store and Google Play apps. Each item: store, app id and name, country, rating (1-5), title, review text, date, app version, helpful votes, developer reply and link. Filter by star rating (e.g. min 1 / max 2 for complaints only). Apps can be App Store URLs or IDs…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| apps | array | yes | App Store / Google Play URLs, IDs, package names or app names. |
| max_reviews_per_app | integer | no | Per app and country. The App Store returns at most 500. |
| countries | array | no | Two-letter country codes, e.g. ['us', 'gb']. |
| sort | string | no | Which reviews come first. |
| language | string | no | Google Play review language, e.g. en, es, de. |
| min_rating | integer | no | Keep reviews with at least this many stars. |
| max_rating | integer | no | Keep reviews with at most this many stars. |
List open jobs from any company's Workday career site (*.myworkdayjobs.com). Each item: title, requisition id, location, posted-on text, job URL, company; with include_description also job type, remote type, country, apply link, stated pay range and description text. Cost: $1.00 per 1,000 jobs on…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| career_site_urls | array | yes | Workday jobs pages, e.g. https://nvidia.wd5.myworkdayjobs.com/NVIDIAExternalCareerSite |
| search_text | string | no | Optional keywords, same as the site's search box. |
| location_contains | string | no | Optional. Keep jobs whose location contains this. |
| posted_within_days | integer | no | Optional. Only jobs posted in the last N days. |
| include_description | boolean | no | Load full description, pay range and apply link. Slower, same price. |
| max_items | integer | no | Stop after this many jobs in total. |
List open jobs from company job boards on Greenhouse, Lever or Ashby. Each item: ATS, company, title, department, team, location, remote flag, employment type, posted/updated dates, pay range when published, job and apply URLs, optional description text. Cost: $1.50 per 1,000 jobs on the user's…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| boards | array | yes | Job board links, e.g. https://boards.greenhouse.io/airbnb, https://jobs.lever.co/palantir, https://jobs.ashbyhq.com/openai |
| search_text | string | no | Optional. Keep jobs whose title, department or team contains all these words. |
| location_contains | string | no | Optional. Keep jobs whose location contains this. |
| remote_only | boolean | no | Keep only remote jobs. |
| include_description | boolean | no | Add the job description text. Same price. |
| max_items_per_board | integer | no | Optional cap per board so one big company does not use the whole limit. |
| max_items | integer | no | Stop after this many jobs in total. |
List current remote jobs from Remotive, Remote OK, We Work Remotely, Jobicy, Himalayas and Arbeitnow in one deduplicated list (same company + title is returned once), newest first. Each item: board (sourceName, sourceUrl), title, company, allowed location, job type, pay as posted plus parsed…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search_text | string | no | Optional. Keep jobs whose title, company, category or tags contain all these words, e.g. 'python developer'. |
| location_contains | string | no | Optional. Keep jobs whose allowed-location text contains this, e.g. Europe, USA, Worldwide. |
| posted_within_days | integer | no | Optional. Only jobs posted in the last N days. |
| sources | array | no | Optional. Boards to read; default all six. |
| salary_only | boolean | no | Keep only jobs that show pay. |
| min_yearly_salary | integer | no | Optional. Keep jobs whose top pay, as a yearly amount in the job's own currency, is at least this. |
| include_description | boolean | no | Add the job description text. Same price. |
| only_new_since_last_run | boolean | no | Skip jobs returned by an earlier run on this Apify account (for daily new-job feeds). |
| max_items_per_source | integer | no | Optional cap per board so one big board does not use the whole limit. |
| max_items | integer | no | Stop after this many jobs in total. |
Extract tables from PDF files at public URLs (text-based PDFs, not scans). Each item is one table: source PDF, pages, column names, row count, rows as objects (first 50 shown here), and links to the full table as CSV and Excel. Tables continuing across pages are merged. Cost: $2.00 per 1,000…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pdf_urls | yes | — | |
| pages | string | no | Optional page range, e.g. '1-3,7'. Empty reads every page. |
| strategy | string | no | 'lines' for tables with ruled borders, 'text' for tables aligned with spaces only. |
| first_row_is_header | boolean | no | Use the first row as column names. |
| merge_across_pages | boolean | no | Join a table that continues on the next page. |
| min_rows | integer | no | Ignore tables with fewer data rows than this. |
| pdf_password | no | — | |
| max_tables | integer | no | Stop after this many tables. |
Read bank statement PDFs at public URLs into structured data. Each item is one statement: bank, masked account number, currency, period, opening/closing balance, total credits/debits, a balance check (ok or mismatch), and transactions (date, description, debit, credit, amount, balance; first 150…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pdf_urls | yes | — | |
| date_order | string | no | How to read dates like 03/04/2026: auto-detect, day-first or month-first. |
| pdf_password | no | — | |
| max_statements | integer | no | Stop after this many statements. |
Read invoice PDFs at public URLs into structured data. Each item is one invoice: invoice number, invoice and due dates, vendor, currency, subtotal, tax, total, line items (description, quantity, unit price, amount) and an Excel link. Text-based PDFs only, not scans. Cost: $5.00 per 1,000 invoices…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pdf_urls | yes | — | |
| extract_line_items | boolean | no | Also read item rows. Off = header fields and totals only. |
| pdf_password | no | — | |
| max_invoices | integer | no | Stop after this many invoices. |
Check a list of email addresses at DNS level: valid syntax, whether the domain has mail (MX) records, disposable/temporary domains, role accounts (info@, sales@), free providers, and typo suggestions (gmial.com -> gmail.com). Each item: email, result (valid / invalid / risky / unknown), reason,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| emails | array | no | Email addresses to check, up to 1,000 per call. |
| csv_url | string | no | Or a public CSV link (e.g. Google Sheets 'publish to web' CSV) with an email column. |
| max_results_returned | integer | no | How many result rows to return to the conversation. |
Take a screenshot of public web pages and return an image URL for each (PNG or JPEG, hosted in the user's Apify storage). Each item: url, final URL, HTTP status, page title, screenshotUrl, size and viewport. Cookie banners and ads are hidden by default. Pages behind a login are not supported.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| urls | array | yes | Public page URLs. |
| device | string | no | Window size and browser type. |
| full_page | boolean | no | Whole scrollable page (up to 16,000 px) or just the first screen. |
| image_format | string | no | PNG is sharper, JPEG is smaller. |
| selector | string | no | Optional CSS selector to capture one element, e.g. '#pricing'. |
| delay_seconds | integer | no | Extra wait for animations and late content. |
| dark_mode | boolean | no | Ask the page for its dark color scheme. |
| width | integer | no | Optional viewport width override. |
| height | integer | no | Optional viewport height override. |
Crawl a website from start URLs and check every link, image and script it finds. Each item: link URL, HTTP status, result (ok / broken / blocked, where blocked means the site refused automated checks), error, final URL after redirects, response time, internal or external, anchor text and the pages…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start_urls | array | yes | Pages to start crawling from. |
| only_broken | boolean | no | Return only broken links and problems, not working links. |
| max_pages | integer | no | How many pages of the site to open and read for links. |
| max_depth | integer | no | How many links deep to follow. 0 = start pages only. |
| max_links | integer | no | Upper limit of distinct links checked. |
| check_external | boolean | no | Also check links to other websites (checked, not crawled). |
| check_images_and_scripts | boolean | no | Also check images, scripts, stylesheets and icons. |
No parameter schema on file.
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 adhistory: Google Ads, reviews, jobs, PDFs 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 96 / 100
Release 0.3.0 · scanned 7 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 score96
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestdcf7982c684dc1e8982f762283449e07af6d8941371f24f21be701140c0b66d7
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (13 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| competitor_google_ads | no tags | |
| app_reviews | no tags | |
| workday_jobs | no tags | |
| ats_jobs | no tags | |
| remote_jobs | no tags | |
| pdf_tables | no tags | |
| bank_statement | no tags | |
| invoice | no tags | |
| payslip | no tags | |
| image_tables | no tags | |
| clean_email_list | no tags | |
| website_screenshot | no tags | |
| broken_links | untrusted-input | untrusted-input: keyword "crawl" |
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 digestdcf7982c684dc1e8
Scanned2026-11-07
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 0.3.0. Pin a release below and the command asks for exactly that one.
0.3.0
7 Nov 2026
latestNo release note was published with this version.
0.2.1
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 adhistory: Google Ads, reviews, jobs, PDFs 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.