# Hiring Signal MCP — B2B Buying Intent from Career Pages (`sunny_spade/hiring-signal-mcp`) Actor MCP server for AI agents. Detects buying signals from public ATS feeds (Greenhouse, Lever, Ashby). Returns velocity-scored hiring intelligence — find companies hiring RevOps or sales engineers in real time. Native MCP for Claude, Cursor, and Claude Code. - **URL**: https://apify.com/sunny\_spade/hiring-signal-mcp.md - **Developed by:** [NoCanDo](https://apify.com/sunny_spade) (community) - **Categories:** Jobs, Developer tools, MCP servers - **Stats:** 0 total users, 0 monthly users, 0.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $0.01 / 1,000 results This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## 🎯 Hiring Signal MCP — B2B Buying Intent from Career Pages **Detect when companies are actively building teams — and what they're about to buy. Built MCP-first for AI agents (Claude, Cursor, Claude Code).** > "A company hiring 1 sales engineer is hiring an SE. A company hiring 5 sales engineers in 60 days is *building* a sales engineering function — they're about to buy the tools that function needs." ### Why this exists Sales intelligence platforms charge $49–$446/month for hiring/buying-signal data: | Tool | Price | Hiring data | |---|---|---| | Apollo Basic | $49/seat/month | 30,000 credits/year | | Apollo Professional | $79/seat/month | 48,000 credits/year | | Clay Launch | $167/month | "Track job changes and other signals" | | Coresignal Job API | Enterprise quote | 349M jobs | | **Hiring Signal MCP (this Actor)** | **~$0.30 per agent call** | **Real-time, signal-scored, MCP-native** | For an AI agent making 30 calls/day, this Actor costs ~$9/month vs. a $49+/seat/month subscription. ### Built for AI agents (MCP-first) This is a **Model Context Protocol server**. Agents connect to it directly — no Apify Console clicks required. Once connected, your agent can call: - `analyze_company_hiring(domain)` — full hiring snapshot - `get_buying_signals(domain, role_pattern?, threshold?, window_days?)` — detected purchase intent signals - `compare_hiring_velocity(domains[])` — competitive analysis across up to 10 companies #### Connect from Claude Desktop or Claude Code Add to your `claude_desktop_config.json` (or VS Code MCP config): ```json { "mcpServers": { "hiring-signal": { "command": "npx", "args": ["-y", "mcp-remote", "https://YOUR_USERNAME--hiring-signal-mcp.apify.actor/mcp"], "env": { "APIFY_TOKEN": "your_apify_api_token" } } } } ```` Then ask Claude: *"Find the SaaS companies hiring sales engineers in the US right now and rank them by velocity."* ### How signals are detected (v1: velocity-based) A buying signal fires when: - **3+ open roles** match the same canonical role - **Posted within 60 days** (configurable) - Recency-weighted, with confidence scoring **Confidence boosts:** all-senior matches (+0.10), multi-geography spread (+0.10), 5+ matches (+0.40 cap). **Confidence penalties:** intern/junior matches (−0.20). This is intentionally simple, fast, and deterministic — agents don't have to wait for an LLM to decide. Future versions will add pattern-based signals (specific role combinations) and AI-classified intent. ### ATS coverage Adapter | Status | Scale | Coverage \---|---|---|--- Greenhouse | ✅ Production | 30,000+ companies | ~30% of B2B SaaS (Stripe, Airbnb, Pinterest, most YC alumni) Lever | ✅ Production | 5,000+ companies | ~20% of scaleups (Notion, Brex, Mercury) Ashby | ✅ Production | 3,000+ companies | ~10% of well-funded startups (Linear, Ramp) Workable | ✅ Production | 25,000+ companies | EU mid-market & SMB SmartRecruiters | ✅ Production | 4,000+ companies | Global mid-market & enterprise Workday | ✅ Production | 2,500+ tenants | Fortune 500 & global enterprise Careers-page fallback | ✅ Production | Long-tail | JSON-LD → heuristic links → Gemini rescue **v0.2 covers ~95% of typical B2B targets** across SMB, mid-market, and enterprise. The careers-page fallback catches any company not on a named ATS. ### Output schema (truncated example) ```json { "domain": "stripe.com", "company_name": "Stripe", "total_open_roles": 312, "postings_last_30_days": 47, "postings_last_60_days": 89, "postings_last_90_days": 134, "by_function": { "engineering": 178, "sales": 42, "product": 28, "ops": 19 }, "by_country": {"US": 198, "IE": 31, "GB": 24, "IN": 18, "AU": 12}, "top_technologies": [ {"technology": "ruby", "count": 41}, {"technology": "go", "count": 28} ], "buying_signals": [ { "role_pattern": "Sales Engineer", "matching_roles_count": 7, "window_days": 60, "confidence_score": 0.80, "explanation": "7 open 'Sales Engineer' roles posted in last 60 days across 3 countries — primarily senior+ roles. Pattern suggests active team buildout." } ] } ``` ### Pricing — Pay-per-event You pay only for what the Actor delivers. | Event | Price | When charged | |---|---|---| | `mcp-tool-call` | **$0.05** | Per agent tool invocation | | `company-analyzed` | **$0.20** | Per company processed | | `role-extracted` | **$0.005** | Per role parsed and classified | | `buying-signal-detected` | **$0.10** | Per buying signal that fires | **Worked example.** Agent asks: *"Compare hiring at Stripe, Notion, and Linear."* - 1 MCP tool call: $0.05 - 3 companies analyzed: $0.60 - \~600 roles extracted: $3.00 - 4 buying signals detected: $0.40 - **Total: ~$4.05** Most agent sessions cost $0.30–$2.00 per query. ### Use cases **B2B SaaS marketers:** Find prospects in active buying mode for your category. *"List 50 companies hiring 3+ RevOps roles right now"* → instantly actionable target list. **VC analysts:** Monitor portfolio company growth. *"Compare hiring velocity at all 12 of our Series B portfolio companies"* → leading indicator of execution. **Competitive intel teams:** Track competitor team buildouts. *"Is our top competitor hiring engineers faster than us this quarter?"* **Sales leaders:** Find net-new accounts your AEs haven't found yet. *"Mid-market SaaS companies in NY hiring sales engineers"* → instant pipeline. ### Why use this over the cheaper alternatives? Single-platform job scrapers exist on Apify, but they: 1. Target LinkedIn/Indeed (legally fragile, frequently break) 2. Return raw postings — no signal extraction 3. Can't be called from an AI agent 4. Don't aggregate across multiple ATSes This Actor is **MCP-native, signal-extracting, and ATS-agnostic** — three things no other Actor on the Store currently combines. ### Limitations - **Posted dates are required for velocity signals.** Roles without dates are excluded — this prevents false positives from stale postings. - **No LinkedIn scraping**, ever. We only use public ATS APIs and career pages. This is the legal moat. - **English-only role classification in v1.** Non-English roles are still extracted but not signal-scored. - **Workday discovery requires a link on the company's own careers page.** JS-only Workday embeds fall through to the careers-page adapter. ### Roadmap - v0.3: Pattern-based signals (role combinations indicating specific buying intent) - v0.4: AI-classified buying intent (Gemini reads JDs, infers what tools they're about to buy) - v0.5: Webhook delivery for "alert when company X starts hiring for Y" ### Issues, requests, custom builds Open an issue on the Actor's Issues tab and we'll respond within 24 hours. # Actor input Schema ## `domains` (type: `array`): Optional. List of company domains (e.g., \['stripe.com', 'notion.so']) to analyze in direct mode. Ignored when running in Standby/MCP mode. ## `rolePattern` (type: `string`): Optional. A role description like 'sales engineer' or 'RevOps' for direct mode signal detection. ## `geminiApiKey` (type: `string`): Required for AI role classification. Free tier (1500 requests/day) covers ~10,000 roles classified per day. Never stored — used only during the run/session. ## `proxyConfiguration` (type: `object`): Career pages rarely block scrapers, but residential proxy is safer at scale. ## Actor input object example ```json { "domains": [], "rolePattern": "sales engineer", "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("sunny_spade/hiring-signal-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = {} # Run the Actor and wait for it to finish run = client.actor("sunny_spade/hiring-signal-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call sunny_spade/hiring-signal-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=sunny_spade/hiring-signal-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Hiring Signal MCP — B2B Buying Intent from Career Pages", "description": "MCP server for AI agents. Detects buying signals from public ATS feeds (Greenhouse, Lever, Ashby). Returns velocity-scored hiring intelligence — find companies hiring RevOps or sales engineers in real time. Native MCP for Claude, Cursor, and Claude Code.", "version": "0.1", "x-build-id": "TjAFBsHDQDjmW62DO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sunny_spade~hiring-signal-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sunny_spade-hiring-signal-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sunny_spade~hiring-signal-mcp/runs": { "post": { "operationId": "runs-sync-sunny_spade-hiring-signal-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sunny_spade~hiring-signal-mcp/run-sync": { "post": { "operationId": "run-sync-sunny_spade-hiring-signal-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "domains": { "title": "Company domains to analyze (direct-mode only)", "type": "array", "description": "Optional. List of company domains (e.g., ['stripe.com', 'notion.so']) to analyze in direct mode. Ignored when running in Standby/MCP mode.", "default": [], "items": { "type": "string" } }, "rolePattern": { "title": "Role pattern to find (direct-mode only)", "type": "string", "description": "Optional. A role description like 'sales engineer' or 'RevOps' for direct mode signal detection." }, "geminiApiKey": { "title": "Gemini API key (free at ai.google.dev)", "type": "string", "description": "Required for AI role classification. Free tier (1500 requests/day) covers ~10,000 roles classified per day. Never stored — used only during the run/session." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Career pages rarely block scrapers, but residential proxy is safer at scale.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```