MCP Stepstone MCP Server

<details> <summary><strong>Option 1 · Install with Smithery (Recommended)</strong></summary>

Remote serverstreamable-httpPython

What is the MCP Stepstone MCP server?

MCP Stepstone MCP server exists for a simple reason — assistants are far more useful when they can act on MCP Stepstone directly instead of describing what you should do. Option 1 · Install with Smithery (Recommended).

What you get

  • 🔍 Multi-term Search – Concurrently queries Stepstone for every search phrase you supply and deduplicates duplicate postings
  • 📍 Location Targeting – Supports German postal codes with a configurable radius (1–100 km) for regional searches
  • 🧠 Session-aware Follow-ups – Saves results for one hour so you can request full job details later via get_job_details
  • 🛡️ Robust Validation – Defensive parameter validation, logging, and graceful error messages for malformed requests
  • 🐳 Container & CLI Friendly – Works as a plain Python process or inside Docker; integrates cleanly with Smithery and Claude Desktop

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

What the assistant can call

Once MCP Stepstone is connected, these are the calls the assistant has available:

  • Prerequisites — The Prerequisites tool exposed by this server
  • search_jobs — The search_jobs tool exposed by this server
  • get_job_details — Fetches one stored job and enriches it with full description and metadata

Configuration and credentials

You will need 3 environment variables: LOG_LEVEL, REQUEST_TIMEOUT, USER_AGENT. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.8+ - pip - Internet access to reach Stepstone.de when running real searches

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp stepstone mcp server does with a few real requests.

Choosing this one

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Stepstone's toolset — Prerequisites, search_jobs, get_job_details — is a fair guide to whether it matches your workflow. It is maintained by kdkiss; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP Stepstone's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
PrerequisitesThe Prerequisites tool exposed by this server.
search_jobsThe search_jobs tool exposed by this server.
get_job_detailsFetches one stored job and enriches it with full description and metadata.

How to install the MCP Stepstone MCP server

{
  "mcpServers": {
    "stepstone": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "LOG_LEVEL": "your-value",
        "REQUEST_TIMEOUT": "your-value",
        "USER_AGENT": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.8+ - pip - Internet access to reach Stepstone.de when running real searches
VariableDescriptionRequired
LOG_LEVELConfiguration value read at startup.Optional
REQUEST_TIMEOUTConfiguration value read at startup.Optional
USER_AGENTConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Stepstone to Prerequisites.
  • Use MCP Stepstone to search jobs.
  • Use MCP Stepstone to get job details.

Frequently asked questions

It connects MCP Stepstone to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (Prerequisites, search_jobs, get_job_details) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Stepstone directly.