MCP server

JobsPipe runs a Model Context Protocol server so AI agents and MCP-capable clients (Claude, Cursor, and custom MCP hosts) can search live job postings directly, without you writing any HTTP code.

The server speaks MCP over Streamable HTTP at:

https://mcp.jobspipe.dev/mcp

How it works

The MCP server is a thin layer over the JobsPipe API. You authenticate with the same API key you use for the REST API — a key that starts with jp_live_. The server forwards your requests to the API under that key, so:

• Results, sources, and freshness are identical to the REST API.
• Usage counts against your plan, and your plan's quota and rate limits apply.
• There is no separate login, OAuth flow, or extra secret to manage.

Create or copy a key from your dashboard, then pass it as a bearer token on the connection:

Authorization: Bearer jp_live_xxxxxxxxxxxxxxxxxxxxxxxx

A request without a valid jp_live_ key is rejected with 401 Unauthorized.

Connect a client

Claude Code

claude mcp add --transport http jobspipe https://mcp.jobspipe.dev/mcp \
  --header "Authorization: Bearer jp_live_xxxxxxxxxxxxxxxxxxxxxxxx"

Claude Desktop / other connector UIs

Add a custom connector (remote MCP server) with:

• URL: https://mcp.jobspipe.dev/mcp
• Header: Authorization = Bearer jp_live_xxxxxxxxxxxxxxxxxxxxxxxx

Generic MCP config

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

{
  "mcpServers": {
    "jobspipe": {
      "url": "https://mcp.jobspipe.dev/mcp",
      "headers": {
        "Authorization": "Bearer jp_live_xxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Once connected, the tools below appear automatically and the agent can call them.

Tools

search_jobs

Every filter is optional and combined with AND. The most useful inputs:

A typical agent 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 total_results and a next_cursor for paging) and a data array of normalized postings — title, company, location, country, salary range, seniority, posting date, and the apply URL. See the API reference for the full schema.

Use cases

• Job-search copilots. Give an agent natural-language access to live postings — "find remote senior Rust roles posted this week" becomes a single search_jobs call with filters.
• Sales and recruiting intelligence. New postings are a strong buying and outreach signal. An agent can watch for companies hiring a specific role or stack and feed that into a CRM or sequencing tool.
• Market and hiring-trend research. Use include_total_results 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. Pull normalized postings for a list of company_name_or targets to attach live hiring activity to an existing account list.

Limits and errors

The MCP server inherits your plan's limits from the REST API:

Call list_pricing_plans to see the quota, rate limit, and max results per call for each plan.

Other agent surfaces

Beyond MCP, JobsPipe is discoverable by autonomous agents:

• Agent skills — SKILL.md documents for autonomous discovery at https://jobspipe.dev/.well-known/agent-skills/index.json.
• llms.txt — an agent-friendly index of the site at https://jobspipe.dev/llms.txt. Every content page is also available as raw Markdown.
• OpenAPI spec — the API's machine-readable schema at https://api.jobspipe.dev/openapi.json, and an interactive reference at https://api.jobspipe.dev/docs/reference.