Search millions of jobs from your AI agent with the JobsPipe MCP server

JobsPipe now runs a Model Context Protocol server, so any MCP-capable client - Claude, Cursor, or your own agent - can search live job postings directly. No HTTP plumbing, no SDK, and no API key to paste: you point the client at one URL, sign in with your JobsPipe account when prompted, and the agent gets a search_jobs tool it can call on its own.

https://mcp.jobspipe.dev/mcp

What you can build with it

The MCP server turns “every job posting, one API” into a capability your agent reaches for the same way it reaches for web search. A few things teams are doing with it:

• Job-search copilots. Natural language in, structured postings out. “Find remote senior Rust roles posted this week” becomes a single tool call with the right filters.
• Sales and recruiting intelligence. A new posting is a strong buying and outreach signal. Have an agent watch for companies hiring a specific role or stack and push that into your CRM or sequencing tool.
• Market and hiring-trend research. Ask for totals with date and location filters to size demand - how many remote data-engineering roles opened in the US in the last 14 days.
• Dataset enrichment. Feed a list of target companies and attach their live hiring activity to an existing account list.

How it works

The server is a thin layer over the JobsPipe API. On first connect your client opens a browser window and you sign in with your JobsPipe account - no API key to copy, no header to configure. After that, results, sources, and freshness are identical to the REST API, usage counts against your plan, and your plan quota and rate limits apply.

Connect in one line

With Claude Code:

claude mcp add --transport http jobspipe https://mcp.jobspipe.dev/mcp

For clients that read a JSON config (Cursor and similar), use the streamable-HTTP form:

{
  "mcpServers": {
    "jobspipe": {
      "url": "https://mcp.jobspipe.dev/mcp"
    }
  }
}

When the client prompts, sign in with your JobsPipe account (in Claude Code, run /mcp to authenticate). Once connected, the tools appear automatically.

The search_jobs tool

Every filter is optional and combined with AND - title and description phrases, company names, country codes, employment type, seniority, remote, a posted-after date or max age, plus paging. A typical call:

{
  "job_title_or": ["data engineer"],
  "remote": true,
  "posted_at_max_age_days": 14,
  "limit": 25,
  "include_total_results": true
}

The response mirrors the REST API: a metadata block with a total count and a paging cursor, and a data array of normalized postings - title, company, location, country, salary range, seniority, posting date, and the apply URL. The full filter set and response schema live in the MCP docs.