Mcp

What is Mcp about?

Mcp provides a simple MCP server implementation that exposes job‑search functionality. The server can be called directly by AI models (e.g., Claude Desktop, OpenAI's GPT‑4.1‑mini) to retrieve relevant job listings based on natural‑language queries.

How to use Mcp?

1. Install the server – use UV (Python package manager) with Python > 3.12:

   uv run mcp install server.py
   

2. Configure the client – add the server label (e.g., jobswithgpt) and URL (https://jobswithgpt.com/mcp/) in the tool definition for Claude or OpenAI.
3. Make a request – send a query such as find jobs for python devs in sf through the AI model’s tool call. The model receives formatted job results.

Key features of Mcp

• One‑line installation via UV.
• Seamless integration with Claude Desktop and OpenAI’s tool interface.
• Automatic approval for specific tool names (e.g., search_jobs).
• Returns ready‑to‑use markdown with job titles and application links.

Use cases of Mcp

• Career assistants: embed job‑search capabilities into virtual assistants.
• Recruitment bots: automate candidate sourcing based on location and skill.
• Developer tools: enhance IDE chat assistants with real‑time job data.
• Custom AI agents: allow any MCP‑compatible model to fetch employment listings.

FAQ from the Mcp

Q: Which Python version is required? A: Python 3.12 or newer.

Q: Do I need an API key? A: The public demo at jobswithgpt.com/mcp/ does not require one, but self‑hosted instances may.

Q: Can I add more job sources? A: Yes, extend server.py to query additional job boards and return results in the same format.

Q: Is there a Node.js installation method? A: The official guide uses UV for Python; a Node wrapper is not provided yet.

MCP Create Server

A dynamic MCP server management service that creates, runs, and manages Model Context Protocol (MCP) servers dynamically. This service itself functions as an MCP server and launches/manages other MCP servers as child processes, enabling a flexible MCP ecosystem.

Key Features

...

Configuring Claude Desktop as an MCP Client

1. If you have PRO account, you can directly add as hosted MCP connector (https://jobswithgpt.com/mcp)
2. If you have a free account, you can add a proxy to the hosted MCP.

1. Prerequisites

• Claude Desktop Free (installed)
• Node.js ≥ 18 (for npx)

2. Create or Edit Claude Config

Locate (or create) the Claude Desktop config file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

---

3. Add Local Proxy Definition

Insert this JSON:

{
  "mcpServers": {
    "jobswithgpt": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://jobswithgpt.com/mcp"
      ]
    }
  }
}

---

4. Restart Claude Desktop

Quit Claude Desktop completely and reopen it.

Your new server jobswithgpt should appear in the paperclip menu under Tools.

OpenAI instructions

OpenAI can directly use the server hosted MCP server (https://jobswithgpt.com/mcp)

import asyncio
from agents import Agent, Runner
from agents.mcp.server import MCPServerStreamableHttp
import json

MCP_URL = "https://jobswithgpt.com/mcp"  # your FastMCP streamable HTTP endpoint

async def main():
    async with MCPServerStreamableHttp(params={"url": MCP_URL}, name="jobswithgpt") as server:
        agent = Agent(
            name="jobs-mcp-local",
            mcp_servers=[server],
            instructions=(
                "Use the MCP server tools. First call location_autocomplete to get a geonameid "
                "for 'Seattle', then call search_jobs with keywords=['python'] and that geonameid."
            ),
        )
        res = await Runner.run(agent, "Find machine learning jobs in san francisco.")
        print(res.final_output)

if __name__ == "__main__":
    asyncio.run(main())

Example output

Here are some Python developer job opportunities in San Francisco:

1. Software Engineer - Backend, Product Engineering at Baton
   [Apply here](https://job-boards.greenhouse.io/baton/jobs/4011483007)

2. Senior Backend Engineer at Stellic
   [Apply here](https://job-boards.greenhouse.io/stellic/jobs/4705805007)

3. Software Engineer - Backend at Julius AI
   [Apply here](https://jobs.ashbyhq.com/julius/75f8ef44-4fa4-46fa-b416-c7b697078eca)
etc