Jdl MCP Server

Search 1M+ enriched job listings. Filter by skills, salary, location, and more. Free.

Local serverstdioPython

What is the Jdl MCP server?

Most payments and commerce work still happens through a UI a human drives. Jdl MCP server moves it into the conversation instead. Search 1M+ enriched job listings. Filter by skills, salary, location, and more. Free.

The short version

Search 1,000,000+ enriched job listings from 20,000+ companies directly from Claude, Cursor, Windsurf, or any MCP-compatible AI tool.

The tools it exposes

The server publishes 5 tools. What each one is for:

  • search_jobs — Search and filter jobs by keyword, skills, salary, remote type, seniority, location, date, and more
  • 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

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What it needs from you

Configuration is passed through the environment: JDL_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

This sits in the payments and commerce group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Jdl's toolset — search_jobs, get_job, get_company and 2 more — is a fair guide to whether it matches your workflow. It is maintained by echojobsio; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
search_jobsSearch and filter jobs by keyword, skills, salary, remote type, seniority, location, date, and more.
get_jobGet full details for a specific job including description, requirements, salary, and apply link. Use the job_handle ID from search results.
get_companyGet company profile — industry, size, funding, career page. Accepts domain (stripe.com) or handle.
get_filter_optionsDiscover available filter values with job counts. Great for exploring what's in the dataset.
find_similar_jobsFind jobs similar to a given listing using AI vector similarity. Available for remote + tech jobs.

How to install the Jdl MCP server

{
  "mcpServers": {
    "jobdatalake": {
      "command": "npx",
      "args": ["-y", "@jobdatalake/mcp-server"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
JDL_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Jdl to search jobs.
  • Use Jdl to get job.
  • Use Jdl to get company.

Frequently asked questions

It connects Jdl to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (search_jobs, get_job, get_company, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Jdl directly.