mcp-workplace-program-detector
LocalAbout mcp-workplace-program-detector
An MCP server that checks company sites and job postings for published employee programs, including ERGs, DEI, wellbeing, learning, leave and volunteering. It is for company research and returns the Apify actor’s result through a thin wrapper.
Key features
- 01Detects six employee program families
- 02Scans career and related web pages
- 03Can inspect live ATS job postings
- 04Selects which program families to report
- 05Returns actor results unchanged
Use cases
- 01Research a company's published employee programs
- 02Find benefits language in job postings
- 03Check careers pages for ERG and volunteering information
MCP support
Exposes the `detect_workplace_programs` tool to MCP clients. The server forwards inputs to the Apify actor and returns its output unchanged.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @mambalabsdev/mcp-workplace-program-detectorAPIFY_TOKENSecretApify API token from https://console.apify.com/account/integrationsLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
1Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| domain | string | Yes | Bare domain, for example hubspot.com. Protocol and path are stripped. |
| ats_slug | string | No | Skip ATS discovery and read this Greenhouse, Lever or Ashby board slug directly. |
| programs | array | No | Report only these program families. Omit for all six. A family you do not select reports null on its boolean, its evidence URL and its evidence phrase, never false, and is not counted in program_count. A selected family that is genuinely absent still reports false. Narrowing does not make a run cheaper: the corpus is the same either way, only the matching is narrowed. |
| max_pages | string | No | Sent as a string for Clay. Clamped to 1 to 25. Default: "14". |
| skipCache | enum | No | false uses the 14 day cache, true forces a fresh crawl. Sent as a string for Clay, matching the fleet convention. Default: "false".false | true |
| scan_web_pages | boolean | No | Probes the careers, culture, benefits, DEI and ESG paths. This path finds ERG and volunteering language that job postings omit. Default: true. |
| scan_job_postings | boolean | No | Reads the company's live job bodies from its ATS. This path finds benefits language that marketing pages omit. Default: true. |
Details
From the project READMEWorkplace Program Detector MCP Server
MCP server for the Mamba Labs Workplace Program Detector actor on Apify.
A company domain in, the people programs that company publishes out: employee resource groups, DEI, wellbeing and mental health, learning and tuition support, parental and caregiver leave, and volunteering.
Install
npx -y @mambalabsdev/mcp-workplace-program-detector
Claude Desktop
{
"mcpServers": {
"mamba-workplace-program-detector": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-workplace-program-detector"],
"env": { "APIFY_TOKEN": "your-apify-token" }
}
}
}
Get an Apify token at console.apify.com/account/integrations.
Tool
detect_workplace_programs
A company domain in, the people programs that company publishes out: employee resource groups, DEI, wellbeing and mental health, learning and tuition support, parental and caregiver leave, and volunteering.
| Input | Type | Required | Notes |
|---|---|---|---|
domain | string | yes | Bare domain, for example hubspot.com. Protocol and path are stripped. |
ats_slug | string | no | Skip ATS discovery and read this Greenhouse, Lever or Ashby board slug directly. |
programs | array | no | Report only these families: erg, dei, wellbeing, learning, parental, volunteering. Omit for all six. A family you do not select reports null, never false, and is not counted in program_count. |
scan_job_postings | boolean | no | Reads the company's live job bodies from its ATS. This path finds benefits language that marketing pages omit. |
scan_web_pages | boolean | no | Probes the careers, culture, benefits, DEI and ESG paths. This path finds ERG and volunteering language that job postings omit. |
max_pages | string | no | Sent as a string for Clay. Clamped to 1 to 25. |
skipCache | enum | no | false uses the 14 day cache, true forces a fresh crawl. Sent as a string for Clay, matching the fleet convention. |
max_charge_usd | number | no | Optional spending cap for this call, in USD. The actor stops before any charge that would take the run past this amount and keeps every row already charged. |
Billing
You are charged per domain analyzed, plus a small actor start fee.
Prices from the live pricing record, read 2026-10-16:
| Event | Price per event (USD) | Fires when |
|---|---|---|
domain-analyzed | $0.008 on the Free plan, down to $0.0068 on higher Apify plans | Charged once per domain analyzed, including when the domain turns out to be unreachable or blocked. Every row reports how much of the site was actually read, so a null result is a real answer rather than a failure. |
apify-actor-start | $0.00005 | Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event). |
The current price is on the actor's Apify page. Running this server consumes Apify credits.
What this server does and does not do
It is a thin client for the Apify actor. It passes your input through and returns the actor's output unchanged. Every behavior described above lives in the actor, not here.
Errors are surfaced, never swallowed. An invalid input, an invalid token, an exhausted balance, a timeout, or a run that returns anything other than a dataset all come back as an explicit tool error rather than as an empty result.
Source
The actor is on the Apify Store. This wrapper is MIT licensed.
Built by Mamba Labs
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.