Lever MCP server for AI agents
Let Claude, ChatGPT or your own agent read Lever: 1 typed function through one MCP server. No Lever API key needed.
- Site
- lever.co
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Lever
An MCP server for Lever alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/leverEvery site
One MCP server for Lever and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
listJobsLists every published job on one company's Lever board (jobs.lever.co/{site}).Arguments
Name Type Required companystringYes Returns
LeverBoardinterface LeverSalaryRange { min: number | null; max: number | null; currency: string | null; interval: string | null; // "per-year-salary", "per-hour-wage", … } interface LeverPosting { id: string; title: string; location: string | null; allLocations: string[]; department: string | null; team: string | null; commitment: string | null; // "Full-time", "Intern", … workplaceType: string | null; // "remote" | "hybrid" | "onsite" | "unspecified" country: string | null; url: string; applyUrl: string | null; createdAt: string | null; // ISO salaryRange: LeverSalaryRange | null; } interface LeverBoard { site: string; // e.g. "spotify" boardUrl: string; total: number; postings: LeverPosting[]; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/lever/listJobsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.lever.listJobs("spotify");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.lever.listJobs("spotify"))curl -X POST https://api.bowmark.ai/v1/sites/lever/listJobs \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"company":"spotify"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.lever.listJobs("spotify");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/lever/<function> - OpenAPI
/v1/sites/lever/openapi.json