Web SummitWhich sites do you need? Tell us at the booth or here.

Any website, as a tool for your agent.

Wield calls a site's own internal API from your Chrome, with the session you already have. Your agent gets a typed tool. Your logins never leave your device.

/llms.txt
Claude Desktop via wield-mcpIllustrative session

Find me a train from Berlin to Munich on Friday morning, cheapest first.

  1. find_recipe"train Berlin Munich"
    →bahn.de/search-connectionsread-only · no login
  2. runbahn.de/search-connections
    from: "Berlin Hbf", to: "München Hbf", depart_at: Friday 08:00
    →connections[]in your Chrome, in a www.bahn.de tab

Here are Friday's connections after 08:00, sorted by price.

~/.wield/logs/executor.ndjsonevery request that left this laptop

  1. GETwield.run/api/v1/recipes/bahn.de/search-connections200
  2. GETwww.bahn.de/web/api/reiseloesung/orte200
  3. GETwww.bahn.de/web/api/reiseloesung/orte200
  4. POSTwww.bahn.de/web/api/angebote/fahrplan200
  • wield.run saw one recipe download. Not the stations, not the results.
  • www.bahn.de saw a normal search from your browser.
  • Cookies and passwords never left Chrome.

Works withClaude DesktopClaude CodeCursorCodexAny MCP client

We never see your password.

Cloud agent platforms log in for you, so your passwords and cookies live on their servers. Wield runs the other way around. The recipe runs inside your own Chrome, in a tab of the site you're already logged into, and the site sees an ordinary request from your browser. We see which recipe you downloaded.

Your device

Runs the recipe

  • Chrome extension. Sends the recipe's requests from a tab of the site, with your session.
  • wield-mcp. The MCP server your agent talks to, over stdio. No port is opened.
  • Bridge. Connects the two through a socket only your user account can open.

The site

Answers your browser

  • Gets the recipe's requests from your browser, with your cookies, like a click you made yourself.
  • Only the origins listed in the recipe can be called. Everything else is blocked.

wield.run

Serves recipes

  • Public JSON, the same for everyone, each with a sha256 you can check.
  • Counts the site requests you send us.
  • If you opt in: ok or failed and duration per recipe. Nothing else.
Sent to wield.run
Recipe downloads. Site requests you choose to send. With telemetry on, and it is off by default: recipe id, version, ok or failed, duration.
Sent to the site
The recipe's requests, from your own browser with your own cookies, and only to the origins the recipe lists.
Never leaves your device
Cookies, tokens, passwords, page contents, the parameters you pass, and the results.
Written to your disk
Every outbound request goes into ~/.wield/logs: destination, method, path, status and time. No bodies, no query values. Read it any time.
Writes ask first
A recipe that books or sends something shows you exactly what it will send and waits for you to click Allow. No answer in 120 seconds means no.

Recipes are public. Runs are private.

Three parts. Only the first one is on our servers, and it holds nothing about you.

  1. 1 · wield.run

    Registry

    A recipe is a JSON file: the site's internal API calls for one task, its parameters and how to read the answer. Data, never code. No secrets, no cookies. Anyone can read every recipe.

    GET /api/v1/recipes/bahn.de/search-connections
  2. 2 · your Chrome

    Executor

    The extension runs the recipe as same-origin requests from a tab of the site, with the session you already have. You handle logins and 2FA the way you always do.

    fetch → www.bahn.de only
  3. 3 · your agent

    MCP server

    wield-mcp runs locally over stdio. Claude, Cursor and Codex call find_recipe and run like any other tool and get typed results back.

    npx -y wield-mcp

Sites that work today.

11 recipes on 9 sites, starting with Europe. Each recipe is one task on one site. Health comes from opt-in run reports over the last 7 days.

CHECK24energie.check24.de · DE
Read-only · no loginno reports yet
Deutsche Bahnwww.bahn.de · DE
Read-only · no loginno reports yet
FlixBusshop.flixbus.de · DE
Read-only · no loginno reports yet
idealowww.idealo.de · DE
Read-only · no loginno reports yet
ImmoScout24www.immobilienscout24.de · DE
Read-only · no loginno reports yet
jamedawww.jameda.de · DE
Read-only · no loginno reports yet
Search doctors by specialty and cityjameda.de/search-doctors
Read-only · no loginno reports yet
Kleinanzeigenwww.kleinanzeigen.de · DE
Read-only · no loginno reports yet
Lieferandowww.lieferando.de · DE
Search restaurants that deliver to an addresslieferando.de/search-restaurants
Read-only · no loginno reports yet
Zalandowww.zalando.de · DE
Read-only · no loginno reports yet
Read-only · no loginno reports yet

Same tasks. Two ways to run them.

A browser-driving agent (Browser Use) and Wield recipes run the same tasks on the same sites. We publish success rate, median latency and cost per task, with the raw logs.

SystemSuccessMedian latencyCost per task
Benchmark running

Browser Use and Wield recipes run the same tasks on the same sites. Success rate, median latency and cost per task go here, with the raw logs, when the run finishes. We publish the result whichever way it goes.

Which sites do you need?

Name the site and the task. The most requested sites get recorded first. Leave an email if you want to hear when yours works.

Only used to tell you when the recipe works. Never shown or shared.

Most requested

Live count

No requests yet. Yours will be the first.