Chefkoch MCP server: let your AI agent search recipes by rating and time
Wield is an MCP server that gives your AI agent one Chefkoch tool. The agent can search German recipes by dish or ingredients. It gets back each recipe's title, rating, number of votes, difficulty, preparation time and link. The search needs no login and no cookies. Your passwords and cookies never leave your computer.
Chefkoch Search cooking recipes with rating, difficulty and preparation time
Read-only, no loginPasses the daily check
Parameters (4)
| Metric | Wield recipe | Browser Use + Claude Sonnet 5.5 |
|---|---|---|
| Success | 100% | 100% |
| Median time | 414 ms | 40 s |
| Cost per run | $0 | $0.096 |
9 runs each, 7 November 2026. How we measure
What your agent gets
A Wield recipe is a small public file that describes the request Chefkoch's own search makes. Your agent runs it through wield-mcp, the local MCP server on your computer.
| Recipe | What it does | Login | Status (7 Nov 2026) |
|---|---|---|---|
chefkoch.de/search-recipes | Searches recipes: title, short description, rating, votes, difficulty, preparation time, video flag, Plus paywall flag and link | No | ok, 5 of 5 checks |
The recipe takes a dish or a list of ingredients, a result limit of 10, 20 or 50, a page number, and an option to keep sponsored brand recipes. Difficulty comes back as 1 for simple, 2 for normal and 3 for advanced. The how-to guide shows example prompts.
How a request flows
- You ask your agent for a quick vegetarian lasagne with a rating of at least four stars.
- The agent calls
find_recipe, thenrunwithchefkoch.de/search-recipes. wield-mcppasses the run through a local bridge to the Wield extension in your browser.- The extension sends the request to Chefkoch's recipe search service, api.chefkoch.de.
- The results return to your agent. Nothing passes through wield.run.
What leaves your computer
- One search request to
api.chefkoch.deper run. - Wield never reads, copies or sends your cookies or passwords.
- Results go to your AI app and are marked as website content, so your agent is told not to follow instructions found in them.
- Logs stay on your computer. They never record request bodies or query values.
Recipes are data, not code, and no JavaScript from the registry runs in the page. The registry signs every recipe with Ed25519, and wield-mcp refuses a recipe that is unsigned or has changed. Wield sends no Cookie or Host headers, and it redacts derived tokens from results and logs.
Chefkoch's terms, in plain words
Chefkoch's robots.txt disallows AI training crawlers (ClaudeBot, anthropic-ai, Claude-Web). Chefkoch's terms restrict automated use of its content. Wield runs this recipe only when you ask, one search at a time from your own browser, with one request per search. The scope is set: you start each search, one search per call, from your own browser, with no bulk collection and no purchases. The output has titles, ratings and links, not full recipe texts. Open the link to read the method on chefkoch.de.
Limits and what is not working yet
- In our benchmark, Wield passed 9 of 9 runs. The benchmark covers one search task with three fixed queries.
- Recipes marked as Chefkoch Plus are paywalled. The output flags them, and you need a Plus subscription to read them on the site.
- Brand-sponsored recipes are dropped by default.
- If Chefkoch changes its search service, the recipe can stop working until it is updated.
Every run stops at 12 steps, 40 requests, 5 MB per response or 60 seconds. Pacing is set per site, so a single search cannot run away.
FAQ
Is there an official Chefkoch MCP server?
Not that we know of as of 7 November 2026. Wield's recipe reads the same search service the Chefkoch website uses.
Which AI apps work with it?
Any MCP client. npx -y wield-mcp init sets up Claude Desktop, Claude Code, Cursor and Codex. Claude Desktop also has a one-click bundle on wield.run/install.
Does it need a Chefkoch login?
No. The search needs no login, cookies or tokens.
How fast is it compared with a browser agent?
As of 7 November 2026, in our preliminary benchmark, the recipe passed 9 of 9 runs with a median of 414 ms and no model cost. Browser Use driving Claude Sonnet 5.5 passed 8 of 8 runs, with a median of 39.5 s and $0.10 per run. The full method is on the benchmark page.