HasData Glassdoor

Glassdoor MCP Server

A hosted Glassdoor MCP server that gives Claude, Cursor, Windsurf and any other MCP client two read-only Glassdoor tools. Search job listings by keyword and location, then read one posting in full with the employer rating, the salary figure and its provenance, both as structured JSON, with no Glassdoor partner account and nothing to host.

It reads public Glassdoor job pages that a signed-out visitor can see, on the US site and 22 regional ones.

1,000 free credits every month, no card required, which is 100 Glassdoor calls at the 10-credit rate.

https://mcp.hasdata.com/mcp?apis=glassdoor

• Prompts and resources

Contents

• What you need
• Quick start
• Example prompts
• Tools
• Errors and failure paths
• Pricing, free tier and limits
• Tool selection
• How it compares
• FAQ
• HasData links
• Development
• Contributing
• License

What you need

An MCP client and a HasData API key from the dashboard, free to create with no card, and the free tier covers about 100 calls a month at the 10-credit rate. This is a remote server, so the simplest path is a URL and an x-api-key header, with no container to run. A client that only speaks stdio reaches it through a thin launcher, published as @hasdata/glassdoor-mcp on npm and hasdata-glassdoor-mcp on PyPI, shown below.

Quick start

The server URL is the same for every client. We run it hands-on in Claude Code and Claude Desktop. The other blocks follow each client's own documented format for a remote server.

Clients with OAuth support can add the same URL as a connector and sign in without putting a key in a config file.

Claude Code

claude mcp add --transport http glassdoor "https://mcp.hasdata.com/mcp?apis=glassdoor" \

--header "x-api-key: HASDATA_API_KEY"

Claude Desktop

Settings, then Connectors, then Add custom connector, then paste https://mcp.hasdata.com/mcp?apis=glassdoor and sign in.

For the config-file route, Claude Desktop loads only local (stdio) servers, so it reaches a remote server through a stdio launcher. The @hasdata/glassdoor-mcp package is that launcher, and it reads the key from the environment. Add this to claude_desktop_config.json:

{

"mcpServers": { "glassdoor": { "command": "npx", "args": ["-y", "@hasdata/glassdoor-mcp"], "env": { "HASDATA_API_KEY": "YOUR_KEY" } } } }

For Python instead of Node, swap the launcher for the PyPI package, which uvx runs without a manual install:

{

"mcpServers": { "glassdoor": { "command": "uvx", "args": ["hasdata-glassdoor-mcp"], "env": { "HASDATA_API_KEY": "YOUR_KEY" } } } }

Cursor

~/.cursor/mcp.json for every project, or .cursor/mcp.json for one:

{

"mcpServers": { "glassdoor": { "url": "https://mcp.hasdata.com/mcp?apis=glassdoor", "headers": { "x-api-key": "HASDATA_API_KEY" } } } }

Windsurf

~/.codeium/windsurf/mcp_config.json. Windsurf calls the field serverUrl, not url:

{

"mcpServers": { "glassdoor": { "serverUrl": "https://mcp.hasdata.com/mcp?apis=glassdoor", "headers": { "x-api-key": "HASDATA_API_KEY" } } } }

VS Code

.vscode/mcp.json in the workspace:

{

"servers": { "glassdoor": { "type": "http", "url": "https://mcp.hasdata.com/mcp?apis=glassdoor", "headers": { "x-api-key": "HASDATA_API_KEY" } } } }

Example prompts

Each of these lands on one tool, or on two in sequence when the second needs the URL the first returns.

• Find data engineer roles in Austin, TX and show me only the ones where the employer stated the salary.
• What is the median posted salary for this role in Austin, and how many postings did that come from?
• Read this Glassdoor posting in full and list the required qualifications.
• Which companies hiring for this role have an employer rating above 4?
• Show me postings for this role added in the last week, sorted by recency.
• Compare posted salaries for this role on the UK and the German Glassdoor sites.

A prompt that names a role goes to the listing tool, and reading the full description takes a second call per posting. The listing already carries the salary, the employer rating and the skills, so a comparison across many roles needs one call rather than one per posting.

Tools

Two tools, 10 credits per successful call.

Get Glassdoor job listings

hasdata_glassdoor_listing_getJobListings

A page of postings for a role in a place, 30 to a page.

Returns searchInformation with totalResults and the Glassdoor URL behind the query, a jobs array, and pagination.

Each posting carries title, id, url, location, ageInDays, sponsored, a skills array, a description snippet, a salary object and an employer object with its own rating and logoUrl.

The salary object is the reason this tool is worth more than a job board feed. It reports min, median, max, currency, period and, decisively, source, which is either EMPLOYER_PROVIDED or ESTIMATED. The first is a figure the employer published, the second is Glassdoor's own model. In the sample below, 19 of 30 postings were employer-provided and 10 estimated.

{

"title": "Data Engineer", "id": 1010220057561, "url": "https://www.glassdoor.com/job-listing/data-engineer-esc-region-xiii-JV_IC1139761_KO0,13_KE14,29.htm?jl=1010220057561", "location": "Austin, TX", "ageInDays": 36, "sponsored": false, "skills": ["Azure", "Customer service", "System design"], "salary": { "currency": "USD", "period": "ANNUAL", "min": 82572, "median": 82572, "max": 82572, "source": "EMPLOYER_PROVIDED" }, "employer": { "id": 477452, "name": "Education Service Center Region XIII", "shortName": "ESC Region XIII", "rating": 4.2, "sponsored": false } }

Get Glassdoor job details

hasdata_glassdoor_job_getJobDetails

One posting in full, by its Glassdoor URL.

Returns a job object. On top of the title, salary and employer the listing already gave you, it adds the full description as plain text, the same text as descriptionHtml, a requirements object holding educationRequirements and an experienceRequirements array, an address object with coordinates, datePosted, and an expired flag.

{

"title": "Data Engineer", "employer": { "name": "ESC Region XIII", "url": "https://www.glassdoor.com/Overview/Working-at-ESC-Region-XIII-EI_IE477452.11,26.htm" }, "address": { "country": "United States", "region": "Texas", "city": "Austin, TX", "latitude": 30.26694, "longitude": -97.74278 }, "requirements": { "educationRequirements": "Bachelor's degree", "experienceRequirements": ["Azure", "Customer service", "System design", "Windows", "SQL", "AWS"] }, "salary": { "payCurrency": "USD", "period": "ANNUAL", "min": 82572, "median": 82572, "max": 82572, "source": "EMPLOYER_PROVIDED" }, "datePosted": "2026-09-03T00:00:00", "ageInDays": 36, "expired": false }

Prompts and resources

The server exposes 5 resources, one per parameter whose accepted values are a fixed list. Reading one is cheaper than learning the vocabulary from a rejected call, and it costs no credits. Each URI is hasdata://glassdoor/ .

The list is served without an API key, so a client can read it before a user has signed up.

Errors and failure paths

Plan for these rather than assuming a happy path.

`salary.source` decides whether the figure is a fact or a model output. EMPLOYER_PROVIDED came from the posting. ESTIMATED is Glassdoor's own estimate for the role and market, and mixing the two into one median produces a number that describes neither. Filter on source before you aggregate, and say which set a published figure came from.

A single stated salary arrives as `min`, `median` and `max` all equal. Three of the 30 postings in the sample looked like that. A range of zero is a point figure, not a missing range.

`salary` can be absent, and `period` can be `HOURLY` rather than `ANNUAL`. One posting in the sample c