Glassdoor Salary & Reviews Intel - MCP Server

Model Context Protocol (MCP) server wrapper for glassdoor-salary-intel. Gives AI agents direct, pay-per-call access to logged-out Glassdoor comp benchmarks, rating sub-scores, review themes, and interview intel - no API token required when called over x402 / Skyfire.

What it is

A thin MCP server that exposes the Glassdoor intel engine as five typed tools an AI agent can call. Each tool runs the upstream glassdoor-salary-intel actor against logged-out public Glassdoor pages and reshapes the result into small, deterministic JSON (no full review bodies, no named reviewers). Built for comp-analysis copilots, recruiting agents, candidate-prep bots, and employer-research workflows.

Honest note: each tool call triggers a live upstream run. Glassdoor sits behind Cloudflare and is fetched through a residential proxy, so a single call can take up to a minute under adverse conditions, and an occasional company will come back blocked or unresolved (the tool returns ok=false with a reason rather than crashing).

Tools

Tool	Args	Returns
get_company_overview	company	One slim company record: overall rating, every rating sub-score, recommend-to-friend %, CEO approval %, firmographics.
get_salary_benchmarks	company, role_filter? (list), max_datapoints? (<=100)	Per-role salary datapoint rows (base min/p25/median/p75/max, total comp, currency, sample count) + a one-line median summary.
get_review_intel	company, max_reviews_sampled? (<=300)	One aggregated review-intelligence record: rating histogram, rating trend by year, top pros/cons/advice keyword themes, anonymized excerpts.
get_interview_intel	company	Interview difficulty score/label, candidate experience split, offer rate, interview count, common questions.
compare_companies	companies (list, 2-5)	Slim company records sorted by overall rating, with a one-line comparison summary.

Run modes

• list_tools - emit the tool catalog (free, no charge) including the agentic-payment descriptor.
• call_tool - invoke one tool. Requires tool + args.
• batch - invoke up to 10 {tool, args} calls in one run.

{
  "mode": "call_tool",
  "tool": "get_salary_benchmarks",
  "args": { "company": "Stripe", "role_filter": ["software engineer"], "max_datapoints": 25 }
}

How agents call it

This is a standard Apify actor-as-tool MCP server. Point your MCP host (Claude, OpenAI Responses, LangChain, LlamaIndex) at the Apify MCP endpoint and it will discover the five tools from the list_tools catalog, then call them with call_tool.

This server is also x402 (USDC on Base) and Skyfire ready. When the operator enables Apify MCP monetization, an AI agent can pay per tool call with no pre-provisioned API token. The list_tools response includes a payments descriptor advertising the accepted rails and per-call price. Operators enable rails via environment variables:

Env	Purpose
X402_ENABLED	1 to advertise x402 acceptance
X402_PAY_TO_ADDRESS	receiving wallet (USDC on Base)
X402_PRICE_USD	per-call price advertised (default 0.005)
SKYFIRE_ENABLED	1 to advertise Skyfire acceptance
SKYFIRE_SELLER_ID	Skyfire seller identity

Calls through Apify always bill via standard PPE (mcp_tool_call $0.005 + upstream pass-through); x402/Skyfire are the token-less rails layered on top for direct agents.

Pricing

Flat $0.005 per MCP tool call, plus the upstream glassdoor-salary-intel PPE pass-through billed to the same run (company_record $0.010, salary_datapoint $0.004, review_enrichment $0.008, interview_intel $0.010). A run that returns nothing costs nothing on the upstream side.

Responsible use / data scope

The upstream actor reads only logged-out, public Glassdoor pages (Overview / Salary / Reviews / Interview) - no accounts, no cookies, no ToS acceptance, no login walls. PII is minimized hard: the tools surface salary aggregates, rating sub-scores, and keyword-frequency review themes (plus optional name-stripped short excerpts), never named reviewers, usernames, or full individual review bodies. You are responsible for lawful use of the outputs. See the upstream actor's README for the full data-scope note.

Related Actors

• glassdoor-salary-intel - the non-MCP actor with full input controls, monitor mode, and CSV/HTML artifacts.
• mcp-hiring-signal-intel - MCP twin for live job-postings and hiring-surge intel.

Support

Issues or coverage gaps: open an issue on the actor page, or leave a quick review: https://apify.com/seibs.co/mcp-glassdoor-salary-intel#reviews