# JobDataLake

JobDataLake — a remote MCP server that searches 1M+ job listings from 20,000+ companies, with filters for skills, salary, location and seniority.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 295 installs
- Author: mgao
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/mgao/jobdatalake
- Updated: 2026-04-17
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/jobdatalake

## What it does

Five tools come with this server. `search_jobs` accepts a keyword or a semantic query and narrows the result by location, pay, remote type, seniority and skills. `get_job` pulls the full posting (description, requirements, salary, apply link) using the `job_handle` returned by a search. `get_company` gives a company profile with its open role count, industry, size and careers page, while `find_similar_jobs` returns neighbouring postings by vector similarity.

Setup is a config entry rather than a local process. The server speaks HTTP at `https://jobdatalake--mgao.run.tools`, so you add that URL to your client and the tools show up.

Call `get_filter_options` first. It lists the values the database actually holds (seniority levels, job functions, skills) with counts, which keeps `search_jobs` from filtering on a label nobody uses. The free quota is 500 calls a day and no account is needed; a loop of similar-job lookups across a long shortlist will burn through it.

## Requirements
- Remote server: `https://jobdatalake--mgao.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http jobdatalake https://jobdatalake--mgao.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add jobdatalake --url https://jobdatalake--mgao.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "jobdatalake": {
            "url": "https://jobdatalake--mgao.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "jobdatalake": {
            "type": "http",
            "url": "https://jobdatalake--mgao.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http jobdatalake https://jobdatalake--mgao.run.tools
```

## When to use it
- find roles matching a specific stack and salary range
- pull requirements and the apply link for one posting
- surface similar roles next to a job you already found
- check a company's profile and open role count
- see which filter values exist before querying

## Example prompts
- Search `search_jobs` for remote senior backend roles and show me the closest matches.
- Take the `job_handle` from that result and pull the requirements with `get_job`.
- Which seniority levels does `get_filter_options` return?

## Similar
- [JobsPipe](https://affpapa.org/en/nevibecode/mcp/jobspipe.md) — MCP server
- [WeJob](https://affpapa.org/en/nevibecode/mcp/wejob.md) — MCP server · ★ 1 repo stars
- [Employed by Guaq AI](https://affpapa.org/en/nevibecode/mcp/employed-by-guaq-ai.md) — MCP server
- [Mind the Product](https://affpapa.org/en/nevibecode/mcp/mind-the-product.md) — MCP server · ★ 3 repo stars
- [ai-dev-jobs-search](https://affpapa.org/en/nevibecode/plugins/ai-dev-jobs-search.md) — plugin · ★ 1013 repo stars
- [HasData Glassdoor](https://affpapa.org/en/nevibecode/mcp/hasdata-glassdoor.md) — MCP server · ★ 7 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
