Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@level-jobs-mcp find remote jobs rated AI level 3"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server (stdio) for Level, a job catalog where every posting is rated on an AI level:
Level | Meaning |
1 | Little AI |
2 | Uses AI |
3 | Works on AI |
4 | Builds AI |
Read-only. No API key. It calls the public REST API documented at https://jobsbylevel.com/developers.
search_jobs: filter by query, AI level range, remote, city, company, recency (max 20 results per page).
get_job: full public record of one job from its slug.
level_lookup: AI level assigned to a job title (optionally at a company).
Related MCP server: mcp-jobs
Claude Desktop / Cursor (mcpServers):
{
"mcpServers": {
"level-jobs": { "command": "npx", "args": ["-y", "level-jobs-mcp"] }
}
}Claude Code:
claude mcp add level-jobs -- npx -y level-jobs-mcpA hosted version (Streamable HTTP, no install) is also available at https://jobsbylevel.com/mcp.
Variable | Default | Purpose |
|
| Base URL of the API (for testing). |
npm install
node index.mjs # speaks MCP over stdioMIT. Job data is served by jobsbylevel.com under its own terms; results link back to the canonical page.
This server cannot be deployed
Free, read-only access to job listings rated by AI level, from Little AI to Builds AI.
Semantic search over 3.5M+ live US job postings pulled straight from company ATSes. Read-only.
Job search over employers' own hiring systems. Search with no key; a free key opens every read tool.
Search AI tools, browse categories and read tool details with source links. Free, read-only access.
