# adhistory: Google Ads, reviews, jobs, PDFs (pypi · adhistory-mcp)

Competitor Google ads, app reviews, job boards, PDF tables/invoices, email checks via Apify

- Trust score: 58/100 (low)
- Change this week: −13
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `adhistory-mcp`: 58/100 (this document), [markdown](https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp.md), [page](https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp)

## Channel facts

- Registry: `pypi`
- Package: `adhistory-mcp`
- Version: `0.11.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Build provenance is cryptographically sound, but it attests a different repository to the one declared in the registry. Most often the declared URL is simply stale.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 7801 tokens (~325/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 39/100
  - Stability check failed: the tool surface changed between 0.3.0 and 0.11.0: 1 tool removals, 0 breaking changes, 12 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Registry listing versus package

Where what the registry lists and what we observed about the package disagree. This view is read from the stored diagnostics trace and is never an input to the score. Each row links to its evidence.

### Repository

- Registry says: `https://github.com/OBrandon/adhistory-mcp`
- Package shows: `OBrandon/small-bets`
- What it means: The attestation is cryptographically sound but binds a different repository to the one the registry declares. Most often the declared URL is simply stale.
- Evidence: https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp#diagnostics-provenance

## Install

### How do I install the adhistory: Google Ads, reviews, jobs, PDFs MCP server?

adhistory: Google Ads, reviews, jobs, PDFs runs locally as a PyPI package, launched with uvx adhistory-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add obrandon-adhistory-mcp -- uvx adhistory-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "obrandon-adhistory-mcp": {
      "command": "uvx",
      "args": [
        "adhistory-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "obrandon-adhistory-mcp": {
      "command": "uvx",
      "args": [
        "adhistory-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add obrandon-adhistory-mcp -- uvx adhistory-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "obrandon-adhistory-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "adhistory-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add obrandon-adhistory-mcp --command uvx --arg adhistory-mcp
```

### Hermes

```yaml
mcp_servers:
  obrandon-adhistory-mcp:
    command: "uvx"
    args: ["adhistory-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "obrandon-adhistory-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "adhistory-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add obrandon-adhistory-mcp -t stdio -c uvx -a adhistory-mcp
```

### Other

```json
{
  "mcpServers": {
    "obrandon-adhistory-mcp": {
      "command": "uvx",
      "args": [
        "adhistory-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 58, +1)

- [security improvement] Malware scan: unverified → pass
- [functional] Package version: 0.10.0 → 0.11.0

### 2026-11-20 (score 57, 0)

- [security improvement] Malware scan: unverified → pass
- [functional] Package version: 0.9.0 → 0.10.0

### 2026-11-19 (score 57, 0)

- [security improvement] Malware scan: unverified → pass
- [functional] Package version: 0.8.0 → 0.9.0

### 2026-11-18 (score 57, +1)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Schema quality: 5731 → 6575
- [functional] Package version: 0.7.0 → 0.8.0

### 2026-11-17 (score 56, −16)

- [security regression] Malware scan: pass → unverified
- [security regression] Stability: 0.30 → fail
- [functional regression] Schema quality: 257 → 301
- [functional regression] Schema quality: 257 → 298
- [functional] Schema quality: good → excellent
- [functional] Package version: 0.5.2 → 0.7.0
- [functional] Package version: 0.5.2 → 0.6.0

### 2026-11-15 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 71, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-12 (score 55, 0)

- [security improvement] Malware scan: unverified → pass
- [functional] Package version: 0.5.1 → 0.5.2

## MCP tools (24)

### `competitor_google_ads` (~406 tokens)

Competitor Google ads (Ads Transparency Center)

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, per-country regions and platforms, and the Transparency Center link. Newest ads first; long-running ads are the proven ones. mode='advertiserCheck' returns one row per domain instead (advertises on Google yes/no, estimated ad count, live now, last ad date), useful to qualify a list of companies. Google does not publish spend or keywords. Cost: $1.00 per 1,000 results (an ad, or a checked domain) on the user's Apify account; the default 20 ads cost about $0.02. Latency: usually 20-90 s, up to 5 min for large requests.

Input parameters:

- `ad_format` (string): text = Google Search ads; image and video cover Display and YouTube.
- `advertiser_ids`: Transparency Center advertiser IDs (start with AR).
- `company_names`: Company names to look up in the Transparency Center; the best match is used.
- `country` (string): Only ads shown in this country. ANY = all countries.
- `date_from`: Optional start date, YYYY-MM-DD.
- `date_to`: Optional end date, YYYY-MM-DD.
- `domains`: Advertiser websites, e.g. ['hubspot.com']. URLs are fine.
- `max_ads_per_advertiser` (integer): Newest ads first. Raise to reach older long-running ads.
- `mode` (string): 'ads' lists ads; 'advertiserCheck' returns one summary row per domain.
- `only_active_ads` (boolean): Keep only ads shown in the last 3 days.
- `platform` (string): Only ads shown on this Google platform.

### `app_reviews` (~280 tokens)

App Store & Google Play reviews

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 (324684580), Google Play URLs or package names (com.spotify.music), or an app name (App Store search). Cost: $0.10 per 1,000 reviews on the user's Apify account; the default 20 reviews per app cost a fraction of a cent. Latency: usually 10-40 s.

Input parameters:

- `apps` (array, required): App Store / Google Play URLs, IDs, package names or app names.
- `countries` (array): Two-letter country codes, e.g. ['us', 'gb'].
- `language` (string): Google Play review language, e.g. en, es, de.
- `max_rating` (integer): Keep reviews with at most this many stars.
- `max_reviews_per_app` (integer): Per app and country. The App Store returns at most 500.
- `min_rating` (integer): Keep reviews with at least this many stars.
- `sort` (string): Which reviews come first.

### `ats_jobs` (~248 tokens)

Greenhouse, Lever & Ashby jobs

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 Apify account; the default 20 jobs cost $0.03. Latency: usually 5-30 s.

Input parameters:

- `boards` (array, required): Job board links, e.g. https://boards.greenhouse.io/airbnb, https://jobs.lever.co/palantir, https://jobs.ashbyhq.com/openai
- `include_description` (boolean): Add the job description text. Same price.
- `location_contains`: Optional. Keep jobs whose location contains this.
- `max_items` (integer): Stop after this many jobs in total.
- `max_items_per_board`: Optional cap per board so one big company does not use the whole limit.
- `remote_only` (boolean): Keep only remote jobs.
- `search_text`: Optional. Keep jobs whose title, department or team contains all these words.

### `bamboohr_jobs` (~360 tokens)

BambooHR jobs

List open jobs from company careers pages on BambooHR (company.bamboohr.com/careers). Each item: title, company, department, employment type, city, state, country, location text, workplace type (on-site/remote/hybrid), remote flag, job and apply URLs; with include_description also posted date, minimum experience, pay text when the employer publishes it, and description text. Same field names as ats_jobs. Honest limits: you supply the companies (it does not discover who uses BambooHR); companies without a public careers page are skipped; most employers publish no pay. Cost: $0.80 per 1,000 jobs on the user's Apify account; the default 20 jobs cost $0.016. Latency: usually 5-30 s (longer with descriptions, about one request per job).

Input parameters:

- `companies` (array, required): BambooHR careers links (https://kiln.bamboohr.com/careers), a job link from that page, or just the part before .bamboohr.com (kiln).
- `department_contains`: Optional. Keep jobs whose department contains this, e.g. sales.
- `include_description` (boolean): Add posted date, pay text, minimum experience and description. Slower, same price.
- `location_contains`: Optional. Keep jobs whose city, state, country or workplace type contains this.
- `max_items` (integer): Stop after this many jobs in total.
- `max_items_per_company`: Optional cap per company so one big employer does not use the whole limit.
- `remote_only` (boolean): Keep only jobs the employer marked as remote.
- `search_text`: Optional. Keep jobs whose title or department contains all these words.

### `workable_jobs` (~377 tokens)

Workable jobs

List open jobs from company career pages on Workable (apply.workable.com/company). Each item: title, company, account, department, job function, employment type, experience level, city, region, country, country code, other locations of the same job, workplace type (remote/hybrid/on_site), remote flag, posted date (day only), job and apply URLs; with include_description also the description as text. Same field names as ats_jobs. Honest limits: you supply the companies (it does not discover who uses Workable); Workable publishes no pay, so pay is always empty; companies with no open jobs return nothing. Cost: $1.00 per 1,000 jobs on the user's Apify account; the default 20 jobs cost $0.02. Latency: usually 5-30 s (one request per company plus one per job).

Input parameters:

- `accounts` (array, required): Workable career page links (https://apply.workable.com/skroutz), a job link from that page, or just the account name from the address (skroutz).
- `departments`: Optional. Keep jobs whose department contains one of these words.
- `include_description` (boolean): Add the full description as text and HTML. Larger output, same price.
- `keywords`: Optional. Keep jobs whose title, department or job function contains any of these words.
- `location_contains`: Optional. Keep jobs whose city, region, country or two-letter country code contains this.
- `max_items` (integer): Stop after this many jobs in total.
- `max_items_per_company`: Optional cap per company so one big employer does not use the whole limit.
- `remote_only` (boolean): Keep only jobs the employer marked as remote.
- `workplace_types`: Optional. Keep only these workplace types.

### `personio_jobs` (~467 tokens)

Personio jobs

List open jobs from company career pages on Personio (company.jobs.personio.de or .com). Each item: title, company (legal entity), account, department, team, office and additional offices, remote flag, employment type (permanent, internship, working student, trainee, fixed-term), schedule (full-/part-time), seniority, years of experience, keyword tags, posted date, salary min/max/currency/period plus a yearly figure and salaryText when the employer publishes it, job and apply URLs; with include_description also the description by section and as text. Same field names as ats_jobs. Honest limits: you supply the companies (it does not discover who uses Personio); most employers publish no salary; remote is read from the office name; texts are often German unless language='en' and the employer translated them. Cost: $0.80 per 1,000 jobs on the user's Apify account; the default 20 jobs cost $0.016. Latency: usually 5-20 s (one request per company).

Input parameters:

- `companies` (array, required): Personio career page links (https://tado.jobs.personio.de), a job link from that page, or just the part before .jobs.personio (tado).
- `departments`: Optional. Keep jobs whose department contains one of these words.
- `employment_types`: Optional, e.g. permanent, intern, working_student, trainee, fixed_term, part-time.
- `include_description` (boolean): Add the description by section and as text and HTML. Larger output, same price.
- `keywords`: Optional. Keep jobs whose title, department, team or keyword tags contain any of these words.
- `language`: Optional two-letter code, e.g. en, for translated job texts.
- `location_contains`: Optional. Keep jobs whose main or additional office contains this, e.g. Berlin.
- `max_items` (integer): Stop after this many jobs in total.
- `max_items_per_company`: Optional cap per company so one big employer does not use the whole limit.
- `remote_only` (boolean): Keep only jobs whose office is Remote, Home office or similar.
- `with_salary_only` (boolean): Keep only jobs with a published salary.

### `recruitee_jobs` (~548 tokens)

Recruitee jobs

List open jobs from company career sites on Recruitee (company.recruitee.com, also when the site runs on the company's own domain). Each item: title, company, account, department, category, tags, location, city, country, country code, all locations of a multi-location job, remote flag, work mode (hybrid/remote/on-site), employment type (permanent, fixed-term, part-time, internship ...), experience level, education level, hours per week min/max, posted date, closing date when set, salary min/max/currency/period plus a yearly figure and salaryText when the employer publishes it, job and apply URLs; with include_description also the description and requirements as text and HTML. Same field names as ats_jobs. Honest limits: you supply the companies (it does not discover who uses Recruitee, and it cannot search all Recruitee jobs); for a site on its own domain you need the Recruitee name (jobs.channable.com is channable); open jobs only; most employers publish no salary, and a range without a period has no yearly figure; a hybrid job has remote=false; companies with no open jobs return nothing. Cost: $0.80 per 1,000 jobs on the user's Apify account; the default 20 jobs cost $0.016. Latency: usually 5-20 s (one request per company).

Input parameters:

- `companies` (array, required): Recruitee career site links (https://bunq.recruitee.com), a job link from that site, or just the part before .recruitee.com (bunq).
- `departments`: Optional. Keep jobs whose department contains one of these words.
- `employment_types`: Optional, e.g. permanent, fixed-term, part-time, internship, contract, freelance.
- `include_description` (boolean): Add the description and requirements as text and HTML. Larger output, same price.
- `keywords`: Optional. Keep jobs whose title, department, category or tags contain any of these words.
- `language`: Optional two-letter code, e.g. en, for translated job texts.
- `location_contains`: Optional. Keep jobs whose city, region, country or work mode contains this, e.g. Amsterdam.
- `max_items` (integer): Stop after this many jobs in total.
- `max_items_per_company`: Optional cap per company so one big employer does not use the whole limit.
- `remote_only` (boolean): Keep only jobs the employer marked as remote.
- `with_salary_only` (boolean): Keep only jobs with a published salary.

### `remote_jobs` (~393 tokens)

Remote jobs from 6 job boards

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 salaryMin/salaryMax/salaryCurrency/salaryPeriod and a yearly figure (salaryYearlyMin/Max), posted date, job and apply URLs, optional description text. Filter by keywords, location, age and pay. Returns what those six boards currently list, not the whole web; currencies are not converted. Cost: $1.00 per 1,000 jobs on the user's Apify account; the default 20 jobs cost $0.02. Latency: usually 5-30 s.

Input parameters:

- `include_description` (boolean): Add the job description text. Same price.
- `location_contains`: Optional. Keep jobs whose allowed-location text contains this, e.g. Europe, USA, Worldwide.
- `max_items` (integer): Stop after this many jobs in total.
- `max_items_per_source`: Optional cap per board so one big board does not use the whole limit.
- `min_yearly_salary`: Optional. Keep jobs whose top pay, as a yearly amount in the job's own currency, is at least this.
- `only_new_since_last_run` (boolean): Skip jobs returned by an earlier run on this Apify account (for daily new-job feeds).
- `posted_within_days`: Optional. Only jobs posted in the last N days.
- `salary_only` (boolean): Keep only jobs that show pay.
- `search_text`: Optional. Keep jobs whose title, company, category or tags contain all these words, e.g. 'python developer'.
- `sources`: Optional. Boards to read; default all six.

### `telegram_posts` (~281 tokens)

Public Telegram channel posts

Read recent posts from public Telegram channels (the t.me/s web preview; no login, private channels and groups cannot be read). Each item: channel, post link and id, text, date, views, reactions, links, hashtags, mentions, emails, media flags, channel subscribers, plus analysis: views vs the channel's median (viewsVsMedian), view rank, view and reaction rate, weekday and hour. Filter by keywords, age and minimum views. Newest posts first; only what Telegram shows publicly. Cost: $0.35 per 1,000 posts on the user's Apify account; the default 20 posts cost $0.007. Latency: usually 5-30 s.

Input parameters:

- `channels` (array, required): Public channels: username (durov), @username or https://t.me/name link.
- `max_items` (integer): Stop after this many posts in total.
- `max_posts_per_channel` (integer): Newest posts to read per channel.
- `min_views`: Optional. Keep posts with at least this many views.
- `only_new_since_last_run` (boolean): Skip posts returned by an earlier run on this Apify account.
- `posted_within_days`: Optional. Stop at posts older than this many days.
- `search_text`: Optional. Keep posts whose text contains all these words.

### `fda_recalls` (~479 tokens)

FDA recalls (food, drug, device)

List FDA recalls of food (incl. cosmetics and supplements), drugs and medical devices from the official openFDA enforcement data. Each item is one recalled product: category, recall number, classification (Class I is most serious), status, recalling firm and its address, product description, lot/code info, reason for recall, distribution pattern, quantity, voluntary or mandated, recall initiation, classification, report and termination dates, brand/generic/manufacturer names when openFDA links them, and the openFDA source link. Filter by keywords (whole words in product, firm or reason), class, status, firm state or country, and date range. Honest limits: recalls appear only after FDA classifies them (often 1 to a few weeks after the company announcement); meat/poultry (USDA), consumer products (CPSC) and vehicles (NHTSA) are not included; state/country filters use the firm's address, not where the product was sold. Cost: $1.00 per 1,000 recalls on the user's Apify account; the default 20 recalls cost $0.02. Latency: usually 5-30 s.

Input parameters:

- `categories`: Optional. Recall databases to read; default all three.
- `classifications`: Optional. Keep only these classes.
- `countries`: Optional. Recalling firm's country as FDA writes it, e.g. ['United States', 'India'].
- `date_field` (string): Which date the range applies to. reportDate = FDA weekly Enforcement Report date.
- `date_from`: Optional start date, YYYY-MM-DD. Overrides last_days.
- `date_to`: Optional end date, YYYY-MM-DD.
- `keywords`: Optional. Keep recalls mentioning any of these, e.g. ['listeria', 'peanut'].
- `last_days` (integer): Recalls from the last N days. 0 = whole history since 2004. Ignored with date_from.
- `max_results` (integer): Stop after this many recalls.
- `only_new_since_last_run` (boolean): Skip recalls returned by an earlier run on this Apify account (for alert feeds).
- `states`: Optional. Two-letter US state codes of the recalling firm, e.g. ['CA'].
- `statuses`: Optional. Keep only these recall statuses.

### `sec_filings` (~489 tokens)

SEC EDGAR filings and key financials

List SEC EDGAR filings for companies by ticker or CIK, straight from SEC's free APIs. mode='filings': each item is one filing with company name, CIK, ticker, form (10-K, 10-Q, 8-K, 4, S-1, DEF 14A, 13F-HR ...), filing date, report date, acceptance time, accession number, 8-K item numbers with plain-English descriptions, links to the main document, filing index and folder, file number, size, XBRL flags, SIC industry, exchange and state of incorporation. mode='financials': one row per 10-K/10-Q (or 20-F/40-F) with XBRL key numbers: revenue, gross profit, operating income, net income, EPS basic/diluted, operating cash flow, total assets and liabilities, equity, cash, long-term debt, shares outstanding, currency. Newest first. Honest limits: metadata and links only, the filing text is not downloaded or searched; XBRL fields can be empty when a company uses its own concept; delisted companies and many funds need a CIK. Cost: $0.40 per 1,000 rows (a filing, or a reporting period) on the user's Apify account; the default 20 rows cost under a cent. Latency: usually 5-30 s (longer for old date ranges).

Input parameters:

- `companies` (array, required): Tickers (AAPL, BRK-B), CIKs (320193) or exact SEC company names.
- `date_from`: Optional. Filed on or after, YYYY-MM-DD.
- `date_to`: Optional. Filed on or before, YYYY-MM-DD.
- `form_types`: Optional. Keep only these forms, e.g. ['10-K', '8-K', '4']. Empty = every form.
- `include_amendments` (boolean): With 10-K also return 10-K/A, and so on.
- `max_filings_per_company` (integer): Newest first. In financials mode, reporting periods per company.
- `max_items` (integer): Stop after this many rows in total.
- `mode` (string): 'filings' lists filings; 'financials' returns XBRL key numbers per 10-K/10-Q.

### `journalist_requests` (~422 tokens)

Journalist requests (#JournoRequest feed)

List recent journalist source requests (#JournoRequest, #PRrequest, #MediaRequest and similar) posted on Bluesky and Mastodon, newest first, with duplicates merged. Each item: source, post URL, posted date, text, author handle, hashtags, language, parsed deadline (date and original text) and expired flag, outlet, request type (expert comment / case study / product / other), topics, how to respond (link, email or DM), links and emails in the post, the request service that posted it, times posted and other post links, likes/reposts/replies. Filter by keywords, age and deadline. Honest limits: roughly 3-10 new requests a day across the default hashtags; X/Twitter, LinkedIn and paid services (HARO/Connectively, Qwoted, Featured) are not included; deadline, outlet, type and topics are parsed from free text on a best-effort basis, so read the request before pitching. Cost: $1.00 per 1,000 requests on the user's Apify account; the default 20 requests cost $0.02. Latency: usually 10-60 s.

Input parameters:

- `exclude_keywords`: Optional. Drop requests mentioning any of these words.
- `hashtags`: Optional. Hashtags to read instead of the defaults (journorequest, prrequest, ...).
- `keywords`: Optional. Keep requests mentioning any of these words, e.g. ['finance', 'startup'].
- `languages`: Optional. Two-letter language codes to keep, e.g. ['en'].
- `max_items` (integer): Stop after this many requests.
- `only_new_since_last_run` (boolean): Skip requests returned by an earlier run on this Apify account (for daily alerts).
- `posted_within_days` (integer): Only requests posted in the last N days.
- `skip_expired` (boolean): Drop requests whose deadline has passed (requests with no deadline are kept).
- `sources`: Optional. Networks to read; default both.

### `pdf_tables` (~264 tokens)

PDF tables to rows

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 tables on the user's Apify account (PDFs with no tables are free). Latency: usually 10-60 s depending on page count.

Input parameters:

- `first_row_is_header` (boolean): Use the first row as column names.
- `max_tables` (integer): Stop after this many tables.
- `merge_across_pages` (boolean): Join a table that continues on the next page.
- `min_rows` (integer): Ignore tables with fewer data rows than this.
- `pages`: Optional page range, e.g. '1-3,7'. Empty reads every page.
- `pdf_password`: Optional. Password for protected PDFs. Leave empty otherwise.
- `pdf_urls` (array, required): Direct public links to PDF files (https://...). The file must download without a login.
- `strategy` (string): 'lines' for tables with ruled borders, 'text' for tables aligned with spaces only.

### `bank_statement` (~210 tokens)

Bank statement PDF to transactions

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 shown here) plus an Excel link with all rows. Text-based PDFs only, not scans. Cost: $15.00 per 1,000 statements ($0.015 each) on the user's Apify account. Latency: usually 10-40 s.

Input parameters:

- `date_order` (string): How to read dates like 03/04/2026: auto-detect, day-first or month-first.
- `max_statements` (integer): Stop after this many statements.
- `pdf_password`: Optional. Password for protected PDFs. Leave empty otherwise.
- `pdf_urls` (array, required): Direct public links to PDF files (https://...). The file must download without a login.

### `invoice` (~177 tokens)

Invoice PDF to data

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 ($0.005 each) on the user's Apify account. Latency: usually 10-30 s.

Input parameters:

- `extract_line_items` (boolean): Also read item rows. Off = header fields and totals only.
- `max_invoices` (integer): Stop after this many invoices.
- `pdf_password`: Optional. Password for protected PDFs. Leave empty otherwise.
- `pdf_urls` (array, required): Direct public links to PDF files (https://...). The file must download without a login.

### `payslip` (~190 tokens)

Payslip PDF to data

Read payslip PDFs at public URLs into structured data. Each item is one payslip: employee, employer, pay period and pay date, gross pay, tax, deductions, net pay, earnings lines (hours, rate, amount) and deduction lines, plus an Excel link. Text-based PDFs only, not scans. Cost: $5.00 per 1,000 payslips ($0.005 each) on the user's Apify account. Latency: usually 10-30 s.

Input parameters:

- `extract_lines` (boolean): Also read earnings and deduction rows. Off = header fields and totals only.
- `max_payslips` (integer): Stop after this many payslips.
- `pdf_password`: Optional. Password for protected PDFs. Leave empty otherwise.
- `pdf_urls` (array, required): Direct public links to PDF files (https://...). The file must download without a login.

### `image_tables` (~162 tokens)

Table in an image to data

Read tables out of pictures (screenshots, photos of printed tables; PNG, JPG, WEBP, BMP, TIFF) at public URLs using OCR. Each item is one table: rows and columns as text, the OCR confidence, plus CSV and Excel links. Honest limit: OCR can misread small or blurry text, so check numbers that matter. Cost: $2.00 per 1,000 tables ($0.002 each) on the user's Apify account. Latency: usually 10-40 s.

Input parameters:

- `first_row_is_header` (boolean): Use the first row as column names.
- `image_urls` (array, required): Direct public links to table images (https://...).
- `max_tables` (integer): Stop after this many tables.

### `word_tables_to_excel` (~315 tokens)

Word document tables to rows

Extract every table from Word documents at public URLs. Each item is one table: source document, table number, the heading written above it, column names, row count, rows as objects keyed by the header (first 50 shown here), and links to the table as CSV and to the document's Excel file (one sheet per table). Merged cells are repeated into every cell they span; numbers like 1,250 come back as numbers. Honest limits: .docx files and Google Docs shared as 'Anyone with the link' only; old .doc (Word 97-2003), PDF, .odt and .rtf are not read; links must download without a login. Use 'sample' as a link to try a built-in example. Cost: $1.50 per 1,000 tables on the user's Apify account (documents that fail or have no tables are free). Latency: usually 10-30 s.

Input parameters:

- `doc_urls` (array, required): Links to .docx files or shared Google Docs (https://...), reachable without a login.
- `first_row_is_header` (boolean): Use each table's first row as column names.
- `include_nested_tables` (boolean): Also return tables nested inside table cells.
- `max_tables` (integer): Stop after this many tables.
- `min_rows` (integer): Skip tables with fewer data rows than this.
- `repeat_merged_cells` (boolean): Copy a merged cell's value into every cell it spans.

### `html_tables_to_excel` (~348 tokens)

Web page HTML tables to rows

Extract the data tables from public web pages (HTML <table> elements). Each item is one table: page URL, table number, its caption or the heading above it, column names (two-row headers joined), row count, rows as objects keyed by the header (first 50 shown here), and links to the table as CSV and to the page's Excel file (one sheet per table). Merged cells are repeated into every cell they span, footnote marks like [1] are removed, and 1,250 / $12.99 / 7.5% come back as numbers. Menus and layout tables are skipped. Honest limits: tables drawn by JavaScript after the page loads are not read; pages behind a login, or that answer 401/403 to automated requests (some large sites do), are reported as failed. Use 'sample' as a link to try a built-in example. Cost: $1.50 per 1,000 tables on the user's Apify account (pages that fail or have no tables are free). Latency: usually 5-30 s.

Input parameters:

- `first_row_is_header` (boolean): Use each table's header row as column names.
- `max_tables` (integer): Stop after this many tables.
- `min_rows` (integer): Skip tables with fewer data rows than this.
- `page_urls` (array, required): Links to public web pages (https://...) that contain HTML tables.
- `repeat_merged_cells` (boolean): Copy a merged cell's value into every cell it spans.
- `skip_layout_tables` (boolean): Skip menus, navigation boxes, infoboxes and single-column layout tables.

### `clean_email_list` (~216 tokens)

Clean an email list (syntax, MX, disposable)

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, score 0-100 and the individual checks. Honest limit: the mailbox itself is NOT checked (no SMTP probe), so a well-formed address on a working domain can still bounce. Duplicates are removed. Cost: $0.20 per 1,000 unique emails on the user's Apify account. Latency: usually 5-30 s.

Input parameters:

- `csv_url`: Or a public CSV link (e.g. Google Sheets 'publish to web' CSV) with an email column.
- `emails`: Email addresses to check, up to 1,000 per call.
- `max_results_returned` (integer): How many result rows to return to the conversation.

### `website_screenshot` (~241 tokens)

Website screenshot

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. Cost: $1.00 per 1,000 screenshots ($0.001 each) on the user's Apify account. Latency: usually 10-30 s per page.

Input parameters:

- `dark_mode` (boolean): Ask the page for its dark color scheme.
- `delay_seconds` (integer): Extra wait for animations and late content.
- `device` (string): Window size and browser type.
- `full_page` (boolean): Whole scrollable page (up to 16,000 px) or just the first screen.
- `height`: Optional viewport height override.
- `image_format` (string): PNG is sharper, JPEG is smaller.
- `selector`: Optional CSS selector to capture one element, e.g. '#pricing'.
- `urls` (array, required): Public page URLs.
- `width`: Optional viewport width override.

### `broken_links` (~254 tokens)

Broken link checker

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 it was found on. By default only problems are returned. Cost: $1.00 per 1,000 result rows on the user's Apify account (with only_broken, working links are not charged). Latency: usually 20-120 s depending on site size.

Input parameters:

- `check_external` (boolean): Also check links to other websites (checked, not crawled).
- `check_images_and_scripts` (boolean): Also check images, scripts, stylesheets and icons.
- `max_depth` (integer): How many links deep to follow. 0 = start pages only.
- `max_links` (integer): Upper limit of distinct links checked.
- `max_pages` (integer): How many pages of the site to open and read for links.
- `only_broken` (boolean): Return only broken links and problems, not working links.
- `start_urls` (array, required): Pages to start crawling from.

### `ssl_certificates` (~313 tokens)

SSL certificate checker

Check the SSL/TLS certificate of domains by opening a real TLS connection (port 443 by default). Each item is one domain: status (OK / EXPIRING_SOON / EXPIRED / INVALID / UNREACHABLE), problems and error text, days until expiry, valid from/to, issuer, subject, SAN list, hostname match, chain trusted (Mozilla CA bundle) and verify error, self-signed flag, TLS version, cipher, key type and size, signature algorithm, serial, SHA-256 fingerprint, IP and handshake time. Honest limits: public hosts only; no STARTTLS (use ports 465/993/995, not 25/587); no revocation (OCSP/CRL) or cipher-suite audit. Cost: $2.00 per 1,000 domains ($0.002 each) on the user's Apify account; with only_problems, OK domains are not charged. Latency: usually 5-30 s.

Input parameters:

- `domains` (array, required): Domains, hostnames or URLs, e.g. example.com, https://shop.example.com/cart, mail.example.com:993.
- `expiry_warning_days` (integer): Certificates expiring within this many days get EXPIRING_SOON.
- `only_problems` (boolean): Return only domains whose status is not OK.
- `port` (integer): TLS port for entries without their own :port.
- `timeout_secs` (integer): Connection and handshake timeout per domain before UNREACHABLE.

### `read_google_sheet` (~209 tokens)

Read a public Google Sheet

Read one tab of a Google Sheet into rows. Each item is one row as an object keyed by the header row's column names; numbers come back as numbers. Works on sheets shared as 'Anyone with the link can view' (no Google login or credentials); private sheets fail. Pick the tab by name, or by the #gid in the URL (default: the first tab). Cost: $0.10 per 1,000 rows on the user's Apify account; the default 200 rows cost about $0.02. Latency: usually 10-30 s.

Input parameters:

- `header_row` (integer): Row that holds the column names.
- `max_rows` (integer): Stop after this many data rows.
- `sheet_name`: Optional tab name. Empty uses the tab in the URL, else the first tab.
- `spreadsheet` (string, required): Google Sheets URL (https://docs.google.com/spreadsheets/d/.../edit#gid=...) or the spreadsheet ID.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp#diagnostics

## Score history

- 2026-11-21: 58
- 2026-11-20: 57
- 2026-11-19: 57
- 2026-11-18: 57
- 2026-11-17: 56
- 2026-11-16: 72
- 2026-11-15: 72
- 2026-11-14: 71
- 2026-11-13: 71
- 2026-11-12: 55
- 2026-11-11: 55
- 2026-11-10: 69
- 2026-11-09: 69
- 2026-11-08: 68
- 2026-11-07: 53

## Common questions

### What is the adhistory: Google Ads, reviews, jobs, PDFs MCP server?

adhistory: Google Ads, reviews, jobs, PDFs is an MCP server listed in the public MCP registry as io.github.OBrandon/adhistory-mcp. Competitor Google ads, app reviews, job boards, PDF tables/invoices, email checks via Apify. This page covers its PyPI package (adhistory-mcp).

### Is the adhistory: Google Ads, reviews, jobs, PDFs MCP server safe to use?

adhistory: Google Ads, reviews, jobs, PDFs scores 58 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the adhistory: Google Ads, reviews, jobs, PDFs MCP server expose?

adhistory: Google Ads, reviews, jobs, PDFs exposes 24 tools: competitor_google_ads, app_reviews, ats_jobs, bamboohr_jobs, workable_jobs, and 19 more. Their descriptions and schemas cost roughly 7,649 tokens of context every time the server is loaded.

### Is the adhistory: Google Ads, reviews, jobs, PDFs MCP server still maintained?

adhistory: Google Ads, reviews, jobs, PDFs is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the adhistory: Google Ads, reviews, jobs, PDFs MCP server under?

adhistory: Google Ads, reviews, jobs, PDFs declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the adhistory: Google Ads, reviews, jobs, PDFs MCP server?

VerifyMCP ran 14 checks on adhistory: Google Ads, reviews, jobs, PDFs, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about adhistory: Google Ads, reviews, jobs, PDFs: Malware scan and Provenance. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/adhistory-mcp/
- Socket report: https://socket.dev/pypi/package/adhistory-mcp
- Repository: https://github.com/OBrandon/adhistory-mcp
- Website: https://apify.com/adhistory
- Changelog RSS feed: https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp.json
- HTML version of this page: https://verifymcp.io/servers/obrandon-adhistory-mcp/adhistory-mcp
