A
licenseA
qualityD
maintenanceAn MCP server that runs Apify scraping actors with quality-gated validation, scoring, and retries, returning embedding-ready chunks for AI agents.
7
1
MIT
actors-mcp
by fecklesspleb
Enables keyword search of Hacker News stories and comments through Algolia's HN Search API, with filters for points, comments, and date.
Provides tools to retrieve open jobs from Greenhouse-hosted company career sites using Greenhouse slugs, board URLs, or careers pages, with job details such as company, title, location, remote flag, department, employment type, salary, posting date, and URL; also supports directory search.
fecklesspleb-actors-mcp
An MCP server that gives AI agents 14 tools: 10 on by default for SEO audits, page metadata, sitemaps, Hacker News search and job listings, plus 4 opt-in web tools for Markdown crawling, image downloads, screenshots and broken-link checks. Each tool runs one of my public Apify Actors and returns the results in the tool response.
Disclosure: I (fecklesspleb) wrote and maintain this server and every Actor it calls. Runs are billed per result to your own Apify account at the Actors' Store prices, and some of that money comes to me as the Actor developer. This project is not affiliated with or endorsed by Apify, Greenhouse, Lever, Ashby, Workday, Remote OK, We Work Remotely, Jobicy, Hacker News, Y Combinator or Algolia.
Why use this instead of Apify's own MCP server
You don't have to. Apify's official server can run these Actors too:
Hosted:
https://mcp.apify.com?tools=fecklesspleb/website-seo-audit,fecklesspleb/sitemap-extractor(OAuth, or anAuthorization: Bearer <APIFY_TOKEN>header)Local:
npx -y @apify/actors-mcp-server --tools fecklesspleb/website-seo-audit,fecklesspleb/sitemap-extractorwithAPIFY_TOKENset
This server is a smaller, focused option:
The results come back in the tool call. Each call uses Apify's synchronous
run-sync-get-dataset-itemsendpoint, so the agent gets the dataset items directly instead of a run ID to poll.Every call has a dollar cap.
maxCostUsd(default $0.25) is sent to Apify asmaxTotalChargeUsd. A server-side ceiling (default $5) caps what an agent can ask for.Small defaults. When the agent leaves them out, the server sets limits such as 25 jobs, 50 Hacker News items or 10 pages per site. Job descriptions are left out unless the agent asks for them, which keeps responses short.
Input schemas stay current. At startup the server reads each Actor's input schema from its live Apify build, so the tools accept exactly what the Actors accept. If Apify can't be reached, it uses a bundled snapshot.
Related MCP server: The Mine Works MCP servers
Tools
Prices are the Apify Store prices when this was written. The live price is on each Actor's page.
core (5 tools, on by default)
Tool | Actor | What it returns | Price |
| Crawls a site from | $0.003 per page + $0.00005 per run start | |
| For each of | $0.001 per URL + $0.00005 per run start | |
| Every URL in a site's sitemaps (found through robots.txt, or from a sitemap URL you pass) with lastmod, changefreq, priority. Regex and date filters | $0.0002 per URL | |
|
| $0.00015 per item | |
| One deduplicated list of remote jobs from the Remote OK, We Work Remotely and Jobicy feeds, with the source on every job. Keyword, location, salary and date filters | $0.001 per job |
jobs (5 tools, on by default)
Open jobs from company career sites. Each job has the company, title, location, remote flag, department, employment type, salary (when the posting gives one), posting date and URL.
Tool | Actor | Pass | Price |
| Greenhouse slugs ( | $0.001 per job | |
| Lever slugs ( | $0.001 per job | |
| Ashby slugs ( | $0.001 per job | |
| Full Workday career site URLs, e.g. | $0.002 per job | |
| Board URLs or careers pages on Greenhouse, Lever, Ashby, Workday, Workable, Recruitee or Teamtailor (Polymer and HireHive by URL). Use it when you don't know which ATS a company uses | $0.002 per job |
web (4 tools, opt-in: FECKLESSPLEB_TOOLSETS=core,jobs,web or all)
Tool | Actor | What it returns | Price |
| Pages of a site as Markdown or text | $0.0008 per page + $0.00005 per run start | |
| Links to images and files saved in your Apify storage, with size, dimensions, alt text, SHA-256 | $0.001 per file + $0.00005 per run start | |
| Links to PNG/JPEG screenshots (and optional PDFs) saved in your Apify storage | $0.0008 per screenshot + $0.00005 per run start | |
| Broken links and images with the page, link text and status code | $0.003 per broken link ($0.0005 per checked link when |
The "run start" charge is per GB of run memory, once per run.
Every tool also takes maxCostUsd. All other arguments are the Actor's own input fields, described in the tool's input schema.
Setup
You need Node.js 20 or newer and an Apify account. Copy your API token from Apify Console > Settings > API & Integrations.
Claude Desktop, Cursor and other clients that use an mcpServers config:
{
"mcpServers": {
"fecklesspleb-actors": {
"command": "npx",
"args": ["-y", "fecklesspleb-actors-mcp"],
"env": { "APIFY_TOKEN": "<your Apify API token>" }
}
}
}Claude Code:
claude mcp add fecklesspleb-actors --env APIFY_TOKEN=<your Apify API token> -- npx -y fecklesspleb-actors-mcpFrom source:
git clone https://github.com/fecklesspleb/actors-mcp.git
cd actors-mcp
npm ci && npm run build
APIFY_TOKEN=<your Apify API token> node dist/index.jsDocker:
docker build -t fecklesspleb-actors-mcp .
docker run -i --rm -e APIFY_TOKEN=<your Apify API token> fecklesspleb-actors-mcpConfiguration
Variable | Default | Meaning |
| (required for calls) | Your Apify API token. Tools are still listed without one, but calls return an error. |
|
| Comma-separated: |
|
| Cap per call when the agent doesn't pass |
|
| Highest |
|
| Run timeout sent to Apify. |
|
| Longest tool response. Longer results are cut short, and the response says how many items were left out. |
|
| Set to |
|
| API base URL. Only for testing against a mock API; leave unset. Must be |
What a call returns
{
"actor": "fecklesspleb/sitemap-extractor",
"itemCount": 2,
"maxCostUsd": 0.25,
"items": [
{ "url": "https://example.com/blog/a", "lastmod": "2026-10-01", "sitemapUrl": "https://example.com/sitemap.xml" },
{ "url": "https://example.com/blog/b", "lastmod": "2026-10-03", "sitemapUrl": "https://example.com/sitemap.xml" }
]
}items are the Actor's dataset items, unchanged. The fields for each Actor are listed on its Apify Store page.
Limits
Apify's synchronous endpoint waits at most 300 seconds. A longer run returns an error, but the run may keep going in your Apify Console. Ask for fewer URLs, pages or companies.
Results larger than
MAX_OUTPUT_CHARSare cut short. The full dataset stays in your Apify account.Screenshots and downloaded files are returned as links to your Apify storage, not as image data.
Development
Building and running the tests needs Node.js 20.19 or newer (on Node 22, 22.12 or newer), because the test runner (Vitest, on Vite 8) requires it. Running the server still needs only Node.js 20 or newer.
npm ci
npm run build
npm test # builds, then runs unit, protocol and token-leak tests against a mocked Apify API, no network
APIFY_TOKEN=<your Apify API token> npm run e2e # one real call (Hacker News, 5 items, about $0.00075, billed to that account)
npm run snapshot-schemas # refresh the bundled input schemas from the live Actor buildsLicense
MIT. Copyright (c) 2026 fecklesspleb.
Available Tools
10 toolsashby_jobsOpen jobs from Ashby job boardsARead-only
Open jobs from companies that hire through Ashby (jobs.ashbyhq.com). Pass companies as Ashby slugs (e.g. 'ramp'), board URLs or careers pages that embed an Ashby board; or set searchDirectory to true to search a built-in directory of boards. Filter with keywords, excludeKeywords, locations, remoteOnly and postedWithinDays. Full descriptions are off by default here to save tokens; set includeDescription to true to get them. Not affiliated with Ashby. Cost, charged to your own Apify account: $0.001 per job returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxTotalJobs=25, includeDescription=false. Runs Apify Actor fecklesspleb/ashby-jobs-scraper (https://apify.com/fecklesspleb/ashby-jobs-scraper).
Inputs: keywords, companies, locations, maxCostUsd, +15 more.
ats_jobsOpen jobs from any of 9 applicant tracking systemsARead-only
Open jobs from company career pages on Greenhouse, Lever, Ashby, Workday, Workable, Recruitee and Teamtailor (Polymer and HireHive by URL), normalised into one schema. Use it when you have a mix of companies or do not know which ATS a company uses; pass board URLs or careers pages in companies. Also filters by salary, seniority, work arrangement and staffing agencies. Filter with keywords, excludeKeywords, locations, remoteOnly and postedWithinDays. Full descriptions are off by default here to save tokens; set includeDescription to true to get them. Not affiliated with any ATS vendor. Cost, charged to your own Apify account: $0.002 per job returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxTotalJobs=25, includeDescription=false. Runs Apify Actor fecklesspleb/ats-jobs-scraper (https://apify.com/fecklesspleb/ats-jobs-scraper).
Inputs: dedupeBy, keywords, companies, hasSalary, +30 more.
extract_sitemap_urlsList the URLs in a site's sitemapsARead-only
Give a site (sitemaps are discovered through robots.txt) or a direct sitemap.xml URL and get every listed URL with lastmod, changefreq and priority. Follows sitemap indexes and reads .gz files. Filter with includePatterns/excludePatterns (regular expressions) and lastmodAfter or lastmodWithinDays. Use it to map a site's pages or find recently changed ones before crawling. Cost, charged to your own Apify account: $0.0002 per URL returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxTotalUrls=500. Runs Apify Actor fecklesspleb/sitemap-extractor (https://apify.com/fecklesspleb/sitemap-extractor).
Inputs: startUrls, maxCostUsd, onlyNewUrls, lastmodAfter, +10 more.
extract_website_metadataExtract page metadata and Open Graph tagsARead-only
Fetch a list of URLs (plain HTTP, no browser) and return each page's title, meta description, canonical URL, language, Open Graph and Twitter card tags, schema.org JSON-LD, favicon, RSS feeds and hreflang links. Use it for link previews, enrichment or quick SEO checks of specific pages. Failed URLs come back as free error rows. Cost, charged to your own Apify account: $0.001 per URL processed; $0.00005 per Actor start (per GB of memory, once per run). Each call is capped at maxCostUsd (default $0.25). Runs Apify Actor fecklesspleb/website-metadata-extractor (https://apify.com/fecklesspleb/website-metadata-extractor).
Inputs: urls (required), maxCostUsd, maxResults, includeJsonLd, +2 more.
greenhouse_jobsOpen jobs from Greenhouse job boardsARead-only
Open jobs from companies that hire through Greenhouse. Pass companies as Greenhouse slugs (e.g. 'airbnb'), boards.greenhouse.io URLs, or careers pages that embed a Greenhouse board; or set searchDirectory to true to search a built-in directory of boards. Filter with keywords, excludeKeywords, locations, remoteOnly and postedWithinDays. Full descriptions are off by default here to save tokens; set includeDescription to true to get them. Not affiliated with Greenhouse. Cost, charged to your own Apify account: $0.001 per job returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxTotalJobs=25, includeDescription=false. Runs Apify Actor fecklesspleb/greenhouse-jobs-scraper (https://apify.com/fecklesspleb/greenhouse-jobs-scraper).
Inputs: keywords, companies, locations, maxCostUsd, +15 more.
lever_jobsOpen jobs from Lever job boardsARead-only
Open jobs from companies that hire through Lever (jobs.lever.co, EU boards included). Pass companies as Lever slugs (e.g. 'palantir'), board URLs or careers pages that embed a Lever board; or set searchDirectory to true to search a built-in directory of boards. Filter with keywords, excludeKeywords, locations, remoteOnly and postedWithinDays. Full descriptions are off by default here to save tokens; set includeDescription to true to get them. Not affiliated with Lever. Cost, charged to your own Apify account: $0.001 per job returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxTotalJobs=25, includeDescription=false. Runs Apify Actor fecklesspleb/lever-jobs-scraper (https://apify.com/fecklesspleb/lever-jobs-scraper).
Inputs: keywords, companies, locations, maxCostUsd, +15 more.
search_hacker_newsSearch Hacker News or its Who is hiring threadsARead-only
mode 'search': search Hacker News stories and comments (including Ask HN and Show HN) by keyword, points, comment count and date through the public HN Search API by Algolia. mode 'whoIsHiring': turn the monthly 'Ask HN: Who is hiring?' thread into job records with company, role, location, remote flag and salary when stated. Emails and phone numbers in post text are redacted by default. Cost, charged to your own Apify account: $0.00015 per item returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxItems=50. Runs Apify Actor fecklesspleb/hacker-news-scraper (https://apify.com/fecklesspleb/hacker-news-scraper).
Inputs: mode, tags, query, since, +13 more.
search_remote_jobsSearch remote jobs (Remote OK, We Work Remotely, Jobicy)ARead-only
One deduplicated list of remote job postings from the official public feeds of Remote OK, We Work Remotely and Jobicy, with the source named on every job. Filter by keywords, excludeKeywords, locations (for example 'USA', 'Europe'), requireSalary, minSalaryUsd and postedWithinDays. Set includeDescription to true for full descriptions. Cost, charged to your own Apify account: $0.001 per job returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxTotalJobs=25. Runs Apify Actor fecklesspleb/remote-jobs-aggregator (https://apify.com/fecklesspleb/remote-jobs-aggregator).
Inputs: dedupe, sources, keywords, jobicyGeo, +14 more.
seo_audit_websiteSEO audit of a websiteARead-only
Crawl a site from one or more start pages (same host only) and audit every page for on-page SEO problems: missing or overlong titles and meta descriptions, H1s, canonicals, noindex, image alt text, thin content, Open Graph, JSON-LD and slow responses. Returns one record per page with a list of issues and a 0-100 score. Use it to find what to fix on a site; use extract_website_metadata instead when you only need the tags of known URLs. Cost, charged to your own Apify account: $0.003 per page audited; $0.00005 per Actor start (per GB of memory, once per run). Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxPagesPerSite=10. Runs Apify Actor fecklesspleb/website-seo-audit (https://apify.com/fecklesspleb/website-seo-audit).
Inputs: startUrls (required), maxCostUsd, maxResults, includeJsonLd, +3 more.
workday_jobsOpen jobs from Workday career sitesARead-only
Open jobs from a Workday career site. Pass companies as full career site URLs as shown in the browser (for example https://nvidia.wd5.myworkdayjobs.com/NVIDIAExternalCareerSite); bare company names are skipped. Also filters by salary, work arrangement, employment type, seniority and years of experience. Filter with keywords, excludeKeywords, locations, remoteOnly and postedWithinDays. Full descriptions are off by default here to save tokens; set includeDescription to true to get them. Not affiliated with Workday. Cost, charged to your own Apify account: $0.002 per job returned. Each call is capped at maxCostUsd (default $0.25). Defaults applied by this server when omitted: maxTotalJobs=25, includeDescription=false. Runs Apify Actor fecklesspleb/workday-jobs-scraper (https://apify.com/fecklesspleb/workday-jobs-scraper).
Inputs: dedupeBy, keywords, companies, hasSalary, +24 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4/5.0
Scored across 10 tools
Disambiguation4/5
The SEO trio (audit vs. metadata extract vs. sitemap) is clearly delineated, with descriptions explicitly cross-referencing each other ('use extract_website_metadata instead when you only need the tags'). The job family is murkier: ats_jobs overlaps directly with greenhouse_jobs, lever_jobs, ashby_jobs and workday_jobs, and only the 'use it when you have a mix of companies or do not know which ATS' phrasing keeps the boundary inferable. search_hacker_news also bundles two unrelated modes (keyword search vs. whoIsHiring job parsing) into one tool.
Naming Consistency3/5
Two patterns coexist: verb_noun for the web tools (seo_audit_website, extract_website_metadata, extract_sitemap_urls) and search_* for two more, but the job tools are bare noun phrases (greenhouse_jobs, lever_jobs, workday_jobs, ats_jobs) with no verb. Names are readable and snake_case throughout, but the verb-first vs. resource-first split is inconsistent. The server name 'actors-mcp' also signals nothing about the SEO/jobs split.
Tool Count5/5
Ten tools is a well-scoped set, and each one maps to a concrete Apify Actor with a real purpose rather than filler. The per-vendor job scrapers are redundant-ish but each targets a genuinely different source API.
Completeness4/5
The SEO side covers discovery (sitemap), diagnosis (audit) and per-URL metadata extraction, which is a coherent lifecycle with no obvious dead end. The jobs side covers major ATS vendors plus an aggregator and remote feeds, but has no follow-up tool to fetch a single job's full detail later (you must re-run with includeDescription) and no cross-tool aggregation of the vendor results.
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
17 data tools in one MCP server, run on Apify: Google Shopping, Flights, Hotels, News, Images, Videos, Ads Transparency, Jobs and Trends; YouTube transcripts; AI visibility checks; Google Maps leads; App Store and Google Play reviews. Pay per result. Sign in with Apify (OAuth) or an API token.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceSeven remote MCP servers exposing 51 published Apify scrapers as agent tools: company diligence, social listening, recruiting, real estate, lead generation, e-commerce and academic research. Billed per result, and a call that returns nothing is never charged.1MIT
- AlicenseAqualityBmaintenanceThis MCP server equips AI agents with ten web-data tools for web search, page reading, site crawling, contact and tech-stack detection, company profiling, e-mail/DNS security checks, e-mail validation, package health, and raw Google search. Each call runs Actors on the user's own Apify account, returning trimmed, readable dataset rows.10MIT
- AlicenseBqualityBmaintenanceMCP server for Ross AI Apify actors (sitemap, SEO, Google Trends, screenshots, app reviews, Markdown). Bring your own APIFY_TOKEN.6MIT
