Let Claude search Swiss job ads on jobs.ch by title and place

#What you need

• Claude Desktop, Claude Code, Cursor, Codex or another MCP client.
• A Chromium browser (Chrome, Edge, Brave, Arc, Vivaldi, Opera or Chromium) with the Wield extension.
• wield-mcp. Run npx -y wield-mcp init, or use the one-click Claude Desktop bundle on wield.run/install.

For the full setup, follow the quick start.

#Ask your agent

Give a job title, skill or company as the search term. Add a city, canton or postcode if you want to narrow the place.

You: Find Python jobs in Zürich on jobs.ch and show title, company, place and link.

Claude calls find_recipe to find the recipe, then run with jobs.ch/search-jobs, term set to python and location set to Zürich. It reads each ad from the result and shows you the list.

#Params: what to put where

The search is fuzzy. A term with no real match still returns loosely related jobs, so check the titles before you rely on a result.

#What comes back

The result has term, location, total, page and jobs. total is the number of matches jobs.ch reports, and it can be null. Each job has title, company, place, employment_type, posted_at and url. The title can include the workload, such as 80–100 %. Open the url to read the full ad.

In our check on 7 November 2026, a search for python in Zürich passed all 5 checks in one request, in 548 ms, and returned 121 matches. The recipe reads the job list that the results page publishes as structured data, so each page holds the 20 ads that page shows.

#What leaves your computer

The recipe makes one request, to www.jobs.ch, for one results page. The request goes out from your own browser, not from wield.run. Nothing passes through wield.run. Wield logs the request on your computer only, with method, host, path, status and timing, and never logs bodies or query values. Wield never reads, copies or sends your cookies or passwords.

#Params in practice

Use term for the job itself. Use location only when you want a place. Leave page out for the first page. Ask for page 2 only when your agent needs more than the first 20 ads.

#jobs.ch's terms, in plain words

The site's robots.txt allows the search page. It disallows /api/, login and feature-flag URLs. It has no rules for Claude agents or AI content signals. The recipe makes one request per call. It does not submit applications, set up job alerts or save bookmarks, and it makes no purchases. Our review of jobs.ch's terms is not finished, and this is not legal advice. Use the recipe for one search that you start yourself, in your own browser, and not for bulk collection of ads. Read the site's terms yourself before you use this recipe in any other way.

#Limits

• Booking and applying stay on jobs.ch. Open the ad's url to apply.
• Each call reads one results page. Don't loop it to watch for new ads.
• location and total can be null.
• A run has at most 12 steps, 40 requests, 5 MB per response and 60 seconds.

#FAQ

#Can Claude apply for a job?

No. The recipe only searches. Open the ad's url to apply on jobs.ch yourself.

#Does it need a login?

No. The search needs no account.

#Why does a made-up search still return jobs?

jobs.ch's search is fuzzy. In our check, a nonsense term still returned about 112 loosely related jobs. Read the titles before you rely on them.

#Which AI apps work with it?

Any MCP client. npx -y wield-mcp init sets up Claude Desktop, Claude Code, Cursor and Codex. See the MCP server page for jobs.ch for the full recipe details.