Job Search MCP for AI Agents

An MCP server that gives Claude, ChatGPT, Gemini, Cursor and any other MCP client three job search tools, straight from company career sites:

Tool	What the agent gets
search_jobs	Open jobs from the career sites of 20,000+ companies (Greenhouse, Lever, Ashby, Workable, Recruitee, Personio, Teamtailor, Gem), indexed every day: search by title words, location, remote, seniority, employment type, skills in the description, salary and visa sponsorship.
list_company_jobs	Every open job of one company, read live from its career site: title, location, remote and workplace type, employment type, seniority, department, salary when published, posting date and apply link. Give the company name or its careers page. Also Workday, Rippling, Breezy and BambooHR.
get_job_details	One job in full: the whole description (responsibilities, requirements, benefits), the salary range when published, years of experience asked, visa sponsorship, locations and the apply link.

Ask your agent things like "Find remote senior data engineer jobs posted this week that publish a salary", "Is Hugging Face hiring in Europe?", "What engineering roles does Stripe have open?" or "Read me the full description of that Notion job and compare it with my CV": it picks the tool and gets clean JSON back. Jobs come from the employers' own career sites, not from aggregators, so there are no reposts and no expired copies. You pay only for results: a company with no open job, or a job that is no longer listed, costs nothing.

Connect your agent

Easiest, with your Apify account (sign-in in the browser, no token to copy): add this remote MCP server URL to your client:

https://mcp.apify.com?tools=digital_influx/job-search-mcp

• Claude (claude.ai, Claude Desktop): add a custom connector with that URL.
• ChatGPT: add it as a connector (MCP server URL) in developer mode.
• Cursor, VS Code, Windsurf, Gemini CLI and other clients: add a remote MCP server. With a token instead of the browser sign-in:

{
  "mcpServers": {
    "job-search": {
      "url": "https://mcp.apify.com?tools=digital_influx/job-search-mcp",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}

(Gemini CLI writes httpUrl instead of url in ~/.gemini/settings.json.)

Directly, without the Apify MCP server: this Actor runs in Standby mode as a Streamable HTTP MCP server. Take its Standby URL from the Actor's API tab in Apify Console, add /mcp, and send your Apify token as Authorization: Bearer YOUR_APIFY_TOKEN.

A record of every call: each tool call your agent makes is also saved as a row of the Standby run's dataset (tool, arguments, a one-line summary and the result), so you can check later what it asked and got. Without an agent: a standard run calls one tool from the input (tool and arguments) and saves the result to the dataset, so the tools also work from the API, schedules and integrations (Make, n8n, Zapier).

The tools

search_jobs

{ "keywords": ["data engineer"], "remoteOnly": true, "postedWithinDays": 7, "onlyWithSalary": true, "limit": 10 }

All arguments are optional: keywords (words in the title), locations (city, country or country code), remoteOnly, seniority (intern, entry, senior, lead, director, executive, unspecified), postedWithinDays, employmentTypes, descriptionKeywords (skills the description must name, e.g. Python; slower, since descriptions are read), onlyWithSalary, onlyVisaSponsorship, companies, limit (10 by default, at most 50) and maxPerCompany (3 by default, so one big employer does not fill the answer). Newest first, without the long descriptions, so the answer stays short for the model. The tool runs the Job Search Actor of the same author in your account and takes 20 to 60 seconds.

list_company_jobs

{ "company": "Stripe", "keywords": ["engineer"], "locations": ["Dublin"], "limit": 20 }

company is a company name ("Airbnb", "Hugging Face"), a careers page URL ("https://jobs.lever.co/spotify", "https://nvidia.wd5.myworkdayjobs.com/NVIDIAExternalCareerSite") or "platform:board" ("ashby:ramp"). A name is looked up in a directory of 20,000+ career sites, rebuilt every month, and otherwise tried as a board name on each platform. Optional filters: keywords, locations, remoteOnly, seniority, postedWithinDays, and limit (20 by default, at most 100). The answer says how many jobs are open and how many match, so "Stripe has 716 open jobs, 144 for engineers" comes in one call, in about a second.

Real result (2026-10-03): Notion, 137 open jobs; with "locations": ["San Francisco"], 74 match, the newest being Payroll Analyst - Accounting, USD 120,000 - 140,000 per year.

get_job_details

{ "platform": "ashby", "companySlug": "notion", "jobId": "92de7ece-b7d9-4b2a-b9cb-b978cc690a46" }

Give the platform, companySlug and jobId that the two other tools return with every job, or the URL of a job page on the platform's own site (job-boards.greenhouse.io, jobs.lever.co, jobs.ashbyhq.com, myworkdayjobs.com...). Returns the description as plain text (up to 12,000 characters; longer ones are cut and say so), the salary with its minimum, maximum, currency and period, yearsOfExperience, visaSponsorship, all locations, department, team and the apply link.

How much it costs

Pay per event, only for results:

Event	When	Price
job	each job list_company_jobs returns	USD 0.002
job-details	each job get_job_details reads in full	USD 0.01

search_jobs charges nothing here: the Job Search Actor it runs bills USD 0.01 per search plus USD 0.006 per job returned. A company with no open job or no career site found, and a job that is no longer listed, cost nothing. Runs in Standby use 256 MB.

Good to know

• Respectful by design: an honest User-Agent (job-search-mcp), only the public job data that each company's career page loads from its job board platform, one company at a time, Lever's crawl delay respected, no proxies and no login.
• Results are what the companies publish. Salary appears when the job board gives it or the description states it (US pay-transparency ranges, for example); Greenhouse boards list no salary until a job is read in full with get_job_details.
• The same engines as the single-purpose Actors of this author: Job Search (the daily index), ATS Jobs Scraper (12 job board platforms), and the Greenhouse, Lever, Ashby and Workday job scrapers, if you want thousands of jobs in one batch or a daily feed of new postings.
• More tools for agents: Company Research MCP (company contacts, the legal entity behind EU websites, new US businesses, tech stack, SEC insider trades and funding rounds) by the same author.