src ▸ client linked0

Give Claude Desktop real web actions on any site

Give Claude Desktop real web actions on any site (login, forms, multi-step tasks) over MCP.

Writ runs on your own accounts, with your own credentials and data, on sites you are authorized to use.
claude_desktop_config.jsonHTTP
HTTP
{
  "mcpServers": {
    "writ": {
      "url": "https://api.usewrit.app/mcp",
      "headers": { "Authorization": "Bearer wt_your_api_key" }
    }
  }
}
read ▸ what it is01
01
what it is

Writ tools, inside the desktop app

Claude Desktop speaks MCP natively. Point it at your Writ server and Claude can call every workflow you save; pin the ones you use most and each becomes its own tool: authenticated, on your own accounts, on sites that have no API of their own.

  1. 1

    Claude reads each tool's description and input schema, so it picks the right Writ workflow for the task on its own.

  2. 2

    Tools run the real browser flow (login, TOTP and mailbox-OTP 2FA, dynamic pages) and hand structured JSON back to the chat.

tools ▸ what they do02
02
tools

What Claude Desktop can do with a Writ tool

Each tool is a saved browser workflow - it acts on the live site, then returns structured output.

⊘

Authenticated actions

Claude Desktop acts on your own accounts - log in, pass TOTP and mailbox-OTP 2FA, then click, fill, and submit. Not a read-only crawl.

◍

Any site, no API required

Each tool is a recorded browser workflow, so it reaches sites that ship no API at all - internal dashboards, vendor portals, no-API web apps.

{ }

Typed, structured output

Every tool returns typed JSON Claude Desktop can read and act on - fields, not raw page text - so the agent can chain the result into the next step.

wire ▸ connect it03
03
connect

Add Writ to Claude Desktop over HTTP

Paste the server block, authenticate with a scoped wt_ key, and every saved workflow is callable - the ones you pin appear as their own tools.

claude_desktop_config.jsonHTTP
HTTP
{
  "mcpServers": {
    "writ": {
      "url": "https://api.usewrit.app/mcp",
      "headers": { "Authorization": "Bearer wt_your_api_key" }
    }
  }
}
  1. 1
    Step 1

    Open Claude Desktop → Settings → Developer → Edit Config.

  2. 2
    Step 2

    Add the "writ" server block to mcpServers with your wt_ API key.

  3. 3
    Step 3

    Restart Claude Desktop; your Writ workflows appear as tools.

What this client getsCall any published workflow as a toolAuthenticated, on your own accounts
{ }

Every workflow is callable; the ones you pin are tools. Anything you save in Writ - a recorded flow, an AI-built workflow, a discovered API - is callable from Claude Desktop through writ_run_workflow; pin a workflow and it shows up as its own tool with a typed schema. See how MCP tools work or read the developer MCP docs.

auth ▸ logged-in web04
04
the hard web

Login, 2FA, and dynamic pages - handled

The sites worth automating are usually the hard ones. Claude Desktop gets tools that handle them.

Because every tool runs the real browser flow, Claude Desktop can complete tasks a read-only MCP server never could: sign in, pass two-factor, navigate pages that render with JavaScript, and submit. It runs on your own accounts and credentials, on sites you are authorized to use.

PersonasTOTP & mailbox OTPAI navigationReal Chromium rendering30+ step types
build ▸ the tool05
05
build

Three ways to author a Claude Desktop tool

All three produce the same callable workflow - which becomes its own tool the moment you pin it.

●

Record it

Do the task once in a real browser; the recorder captures every step into a workflow.

✦

Describe it

Tell an AI session your goal in plain language; it drives the page to build the workflow for you.

⌖

Discover it

Let API discovery watch a site's own network calls as you browse, then turn them into a fast workflow.

faq ▸ questions answered07
07
faq

Claude Desktop + Writ questions

How do I add Writ tools to Claude Desktop?
Open Claude Desktop → Settings → Developer → Edit Config. Add the "writ" server block to mcpServers with your wt_ API key. Restart Claude Desktop; your Writ workflows appear as tools. Every saved workflow is then callable through writ_run_workflow; each one you pin appears as its own tool, selected by its description and typed input schema.
What can Claude Desktop actually do with a Writ MCP tool?
It takes real actions on a website: log in, fill forms, click through multi-step flows, extract fields, and submit - then return structured JSON. Because each tool is a real browser workflow, it works on sites that have no API. Writ runs on your own accounts, with your own credentials and data, on sites you are authorized to use.
Does it handle login and 2FA in Claude Desktop?
Yes. Writ runs the workflow in a real browser on your own account, handling login, TOTP and mailbox-OTP two-factor, and dynamic pages - so the tool completes authenticated tasks the agent could not reach otherwise.
Is this read-only, like most website-to-MCP servers?
No. Most website-to-MCP tools only read page text. Writ tools act - they log in, fill, click, and complete multi-step tasks, then return typed output. Claude Desktop calls the tool; Writ runs the real workflow on your account.
How is a tool authorized?
Every call carries a scoped wt_ API key. You can issue a separate key per project or per Claude Desktop setup, and revoke it without touching the rest.
rec ▸ ready●

Give Claude Desktop tools that act

Publish a workflow once, then call it from your agent as an authenticated, action-taking MCP tool. Get started free.