About Jobdatalake
Jobdatalake is an MCP server for searching enriched job listings from AI tools. It supports detailed filters and job, company, and similar-listing lookups.
Key features
- 01Filter jobs by skills, salary, location, and more
- 02Retrieve full job descriptions and application links
- 03Look up company profiles
- 04Discover filter values and job counts
- 05Find similar listings with AI vector similarity
Use cases
- 01Find remote roles within a salary range
- 02Search openings by seniority or location
- 03Review a listing's requirements before applying
- 04Explore companies or similar job listings
MCP support
Exposes job search and lookup tools to MCP-compatible clients, including search_jobs, get_job, get_company, get_filter_options, and find_similar_jobs.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @jobdatalake/mcp-serverJDL_API_KEYSecretOptional JDL API key for unlimited access. Get one free at jobdatalake.com. Without a key, 500 free calls/day are included.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
5Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| company | string | No | Company domain filter, e.g. "stripe.com" |
| countries | string | No | Comma-separated ISO country codes, e.g. "US,GB,DE" |
| employment_type | enum | No | full_time | part_time | contract | internship |
| job_function | enum | No | eng | data | design | sales | ops | marketing | security | product | finance | hr | legal | other |
| location | string | No | Location filter, e.g. "Remote", "San Francisco", "Germany" |
| page | number | No | |
| per_page | number | No | Results per page (max 100) |
| posted_within | string | No | Time window: "24h", "7d", "30d" — only jobs posted within this period |
| query | string | No | Keyword search (title, company, skills). Use * for all jobs. |
| remote_type | enum | No | Remote work policyfully_remote | hybrid | on_site |
| salary_max | number | No | Maximum annual salary in USD |
| salary_min | number | No | Minimum annual salary in USD |
| semantic_query | string | No | AI semantic search. Works best with job-title-like queries (e.g. "machine learning engineer", "senior devops"). Supported for remote + tech jobs only. |
| seniority | string | No | Comma-separated: Entry, Mid Level, Senior, Staff, Principal, Manager, Internship, Director, Lead, C Level |
| skills | string | No | Comma-separated required skills, e.g. "Python,AWS,Kubernetes" |
| sort_by | string | No | Sort: "posted_at:desc" (newest, default), "posted_at:asc" (oldest), "salary_max_usd:desc" (highest paid), "salary_min_usd:asc" (lowest paid) |
Details
From the project READMEJobDataLake MCP Server
Search 1,000,000+ enriched job listings from 20,000+ companies directly from Claude, Cursor, Windsurf, or any MCP-compatible AI tool.
Free to use — no signup required. 500 calls/day included.
Quick Start
Add to your Claude Code or Claude Desktop MCP config:
{
"mcpServers": {
"jobdatalake": {
"command": "npx",
"args": ["-y", "@jobdatalake/mcp-server"]
}
}
}
That's it. No API key needed. Then ask:
"Find me remote senior React jobs paying over $150k"
"Entry level data science jobs posted this week"
"Jobs at Anthropic paying over $200k"
Want unlimited access?
Sign up at jobdatalake.com for your own API key, then add it:
{
"mcpServers": {
"jobdatalake": {
"command": "npx",
"args": ["-y", "@jobdatalake/mcp-server"],
"env": {
"JDL_API_KEY": "jdl_your_key_here"
}
}
}
}
Tools
search_jobs
Search and filter jobs by keyword, skills, salary, remote type, seniority, location, date, and more.
Filters:
query— keyword search (title, company, skills)skills— AND filter:Python,AWS,Kubernetes(all must match)salary_min/salary_max— in USD (accepts full dollars, e.g. 150000)remote_type—fully_remote,hybrid,on_siteseniority—Entry,Mid Level,Senior,Staff,Principal,Manager,Director,C Levellocation— city, country, or continent (Europe,Asia,Latin America,Scandinavia, etc.)countries— ISO codes:US,GB,DEjob_function—eng,data,design,sales,marketing,product, etc.employment_type—full_time,part_time,contract,internshipposted_within—24h,7d,30dsort_by—posted_at:desc,salary_max_usd:desc,salary_min_usd:asccompany— filter by domain:stripe.com
get_job
Get full details for a specific job including description, requirements, salary, and apply link. Use the job_handle ID from search results.
get_company
Get company profile — industry, size, funding, career page. Accepts domain (stripe.com) or handle.
get_filter_options
Discover available filter values with job counts. Great for exploring what's in the dataset.
find_similar_jobs
Find jobs similar to a given listing using AI vector similarity. Available for remote + tech jobs.
Pricing
Free tier (no signup): 500 calls/day, resets daily.
With your own API key:
- Free: 1,000 credits on signup
- Starter: 1,000,000 credits — $200
- Growth: 2,000,000 credits — $300
- Business: 4,000,000 credits — $400
Credits never expire. Get your API key.
Data
- 1M+ active job listings from 20,000+ companies
- 40+ ATS platforms (Greenhouse, Lever, Workday, Ashby, etc.)
- Updated hourly
- AI-enriched: salary (USD), skills, seniority, remote policy, job function
- Sub-100ms search responses
Example Queries
| Query | What it does |
|---|---|
| "Remote Python jobs over $150k" | Skills + salary + remote filter |
| "Jobs at Stripe" | Company filter |
| "Entry level data science" | Seniority filter |
| "New remote jobs today" | Date + remote filter |
| "React AND TypeScript jobs in Europe" | Multi-skill AND + continent |
| "Highest paying remote jobs" | Salary sort |
| "What skills are most in demand?" | Filter options tool |
License
MIT — see LICENSE.
Support
- Questions: [email protected]
- GitHub: github.com/echojobsio/jdl-mcp-server
- Website: jobdatalake.com
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.