search_jobsLABSCO SUMMARY
Sessions are what make the follow-up question work.
The search returns summaries, and posting bodies are large — so results are held for an hour and a second call pulls the one you asked about. That is the difference between "show me fraud roles near Frankfurt" being one dump of text and being a conversation. Supply either an index or a query to get_job_details, not both; if you pass both, the index wins. The Redis cache mentioned in the README is a future item, not something running today.
What it is
A job-search server for Stepstone.de. It runs several keyword searches concurrently, deduplicates the results, and keeps them for an hour so a follow-up question can fetch one posting in full.
What you get
search_jobstakes an array of search phrases and queries them concurrently, dropping duplicate postings- The same call takes a German 5-digit postal code and a radius between 1 and 100 kilometres — defaults are 40210 and 5
- Results come back with title, company, description snippet and link, grouped per search term, under a session ID
get_job_detailsfetches one stored posting and enriches it with the full description and metadata- It accepts either
job_index— 1-based into the last session's results — orjob_queryas a fuzzy match, withsession_idto target an older session
Requirements
Python 3.8 or higher and internet access to Stepstone.de. Install from a clone with pip install -r requirements.txt and point your client at stepstone_server.py, or run the Docker image. LOG_LEVEL, REQUEST_TIMEOUT (default 10 seconds), USER_AGENT and MAX_RETRIES (default 3) are the tuning knobs.
Setup effort
Build from source
USE CASES
01
Searching several job titles at once
Pass the phrases as a list and get one deduplicated set instead of running three searches.
02
Looking only where you would actually commute
Anchor on a postal code and set the radius in kilometres.
03
Reading the one posting that looked right
Ask for it by position or by name and get the full description and metadata.
04
Coming back to an earlier search
Pass the session ID to fetch details from a set you pulled before.
2 tools
Listed in project docs. Your client may show a different list.
get_job_detailsBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
Python 3.8+
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"stepstone-job-search": {
"command": "python",
"args": [
"<YOUR_PATH_TO_STEPSTONE_SERVER>"
],
"env": {
"LOG_LEVEL": "DEBUG",
"USER_AGENT": "MCP-Stepstone-Bot/1.0"
}
}
}
}
