Give Claude Code real web actions on any site
Give Claude Code callable web actions on any site: one command to add the Writ MCP server.
claude mcp add writ-cloud \
-e WRIT_API_KEY=wt_your_api_key \
-- npx -y writ-mcp Writ tools, inside the coding agent
Claude Code adds MCP servers from a single command. Connect Writ and your agent can drive real websites mid-session (submit a form, export a report, check a dashboard) and read the structured result back into the work.
- 1
One
claude mcp addcommand wires in every workflow you save, plus a tool of its own for each one you pin; scope awt_key per project so a session only sees the tools it should. - 2
The agent acts on the live site as you (not a read-only crawl) so it can complete tasks, not just summarize pages.
What Claude Code can do with a Writ tool
Each tool is an API Writ built from one sentence: it acts on the live site (a real browser only when the site needs one), then returns structured output.
Authenticated actions
Claude Code 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 was built and tested on the live site, 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 Code can read and act on - fields, not raw page text - so the agent can chain the result into the next step.
Add Writ to Claude Code over stdio
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 mcp add writ-cloud \
-e WRIT_API_KEY=wt_your_api_key \
-- npx -y writ-mcp - 1Step 1
Run the claude mcp add command; -e puts your wt_ key in the environment, not in the process list or your shell history.
- 2Step 2
Confirm the server is connected with claude mcp list.
- 3Step 3
Your Writ workflows are now callable tools in the session.
Why this setup is different. Claude Code is a terminal client, so this is the one setup that avoids a pasted HTTP stanza on purpose: a key passed as a --header flag would sit in argv — readable by any local process through ps and written verbatim into your shell history. The writ-mcp connector takes the key as an environment variable via -e instead, and registers as writ-cloud so it never clobbers the Writ desktop app’s own writ server.
Every workflow is callable; the ones you pin are tools. Anything you save in Writ - an API Scribe built, a ready-made one you rebuilt, a recorded step - is callable from Claude Code 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.
Login, 2FA, and dynamic pages - handled
The sites worth automating are usually the hard ones. Claude Code gets tools that handle them.
Because every tool runs the real site flow (a real browser when the site needs one), Claude Code 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.
Three ways to get a Claude Code tool
All three produce the same callable API - which becomes its own tool the moment you pin it.
Describe it
Tell Scribe your goal in one sentence; it drives the live site, tests the result and hands you the API.
Pick a ready-made API
The marketplace lists APIs other people built and Writ checks daily: call one as is in the cloud, or rebuild it locally on Writ Desktop.
Record the difficult part
When a login or a picker needs your hands, click through just that step in a real browser; Writ builds the rest around it.
Use Writ tools in any MCP client
Claude Code + Writ questions
How do I add Writ tools to Claude Code?
What can Claude Code actually do with a Writ MCP tool?
Does it handle login and 2FA in Claude Code?
Is this read-only, like most website-to-MCP servers?
Give Claude Code tools that act
Describe the site once; Writ builds the API, and your agent calls it as an authenticated, action-taking MCP tool. Get started free.