Writ Cloud
Server Details
Turn any website into an API your AI assistant can call. Describe what you need from a site; Writ builds the API, tests it and saves it as a tool, signed in as you when the site needs a login. The same server reads pages to Markdown, crawls sites into datasets and watches pages for changes. Free plan; usage in credits.
- Status
- Healthy
- Uptime
- 50.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- usewrit/writ-mcp
- GitHub Stars
- 1
- Server Listing
- writ-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 41 tools
The scrape/crawl/browser_use/record_website/website_to_api cluster genuinely overlaps, but every description carries explicit 'NOT FOR' routing clauses and the WEB-vs-API framing is consistent. Within families (writ_browser_* 10 tools, crawl lifecycle 6 tools) boundaries are mostly clear, though an agent could still pick record_website when it wanted website_to_api or vice versa.
All names share a writ_ prefix and snake_case, but verb style is mixed: verb_noun (writ_create_monitor, writ_run_workflow), noun-only (writ_personas, writ_devices, writ_payment, writ_help), and listing expressed three different ways (writ_list_workflows, writ_saved_crawls, writ_browser_sessions). Readable, but not a predictable pattern an agent can extrapolate.
41 tools is heavy for a single server, and the surface is further expanded by dynamic run_<name> tools plus a meta-tool (writ_help). Many entries are narrow lifecycle verbs (crawl status, crawl data, run crawl, update crawl, crawl files) that could be consolidated into fewer parameterised tools.
The lifecycle is broad: workflows have list/run/update/schedule/export/pin/expose/diagnose, crawls have create/status/list/save/run/update/data/files, and scraping, personas, payments, monitors, automations and webhooks are all covered. Gaps are mainly teardown/list operations — no delete for workflows, monitors or automations, and monitors/automations can be created but only partially enumerated.
Publisher details
- Operator
- Writ (usewrit.app) · Publisher source
- Operator website
- https://usewrit.app/ · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://usewrit.app/mcp/ · Publisher source
- Privacy policy
- https://usewrit.app/privacy/ · Publisher source
- Trust center
- https://usewrit.app/trust/ · Publisher source
- Restrictions
- Public sign-up with a free plan. Usage is billed in credits; some features (cloud sign-ins, higher check rates) need a paid plan. · Publisher source
Available Tools
41 toolswrit_browser_actAct in a browser sessionADestructiveInspect
Runs one batch of actions on an open session and returns the fresh page. Each action is an object, e.g. {"action":"click","selector":"#go"}. DRIVE: navigate, click, fill, type_text, select, check, hover, submit, press_key, scroll, back, wait, wait_for. SEE: query_dom, find_text, read_text, count, get_attributes, inspect, list_candidates, get_dom, get_screenshot. NETWORK: capture_network, get_request, rotate_exit. CODE: evaluate_js, search_scripts, read_script. RECORD: extract {variable,script}, api_call (a flow is built step by step with writ_browser_compose add_flow_step), login_post, probe_write, confirm_write. 2FA: twofa {challenge_method}. A value written {{name}} with its real value in inputs becomes a workflow input. Each action's arguments: the session's start answer, or writ_help('writ_browser_act').
Inputs: actions (required), session_id (required), inputs, max_chars.
writ_browser_ask_userAsk the user to step inAInspect
Hands an open session to the Writ user: kind='captcha' (they complete a security check in the live browser), 'twofa' (they supply the one-time code and Writ types it; the code never reaches this conversation), 'sign_in' (they sign in on the live page; no persona applies) or 'question' (their text answer). The call that opens the ask returns at once with user_link + tell_user to relay; later calls hold up to 60 s and answer answered, waiting_for_user (the same call again) or expired. Their answer is kept if your turn ends first.
Inputs: session_id (required), kind, question, wait_seconds.
writ_browser_cancelClose a browser sessionADestructiveIdempotentInspect
Closes an open browser session (an open cloud browser bills until it is closed). Unsaved work that did more than visit pages is auto-saved first and the reply names it; discard=true keeps nothing.
Inputs: session_id (required), discard.
writ_browser_composeCompose a workflow in a sessionADestructiveInspect
Authors the workflow in an open session beyond a recording: named API functions (define_function with a flow, preferred in an API build, or a captured call's index or a lists payload; live-tested as defined; compile_function for an authenticated request), set_inputs, add_steps, test_function, remove_function, remove_step, list. A flow is built in small calls: define_function with its first request, then add_flow_step {function, step, at?} per step, each tested and answered with the step list; a set step's value is read as {ref:'vars.'}. Shapes: writ_help('writ_browser_compose').
Inputs: operation (required), session_id (required), payload.
writ_browser_contextRead a browser sessionBRead-onlyIdempotentInspect
Re-reads an open session: section=page (url, fields, buttons, cleaned DOM), lists (the page's repeating rows with a live-tested define_function payload for writ_browser_compose), map (the evidence of the build the session is bound to).
Inputs: session_id (required), offset, section, max_chars.
writ_browser_live_viewLive browser viewCIdempotentInspect
The live browser card's own access: the card ChatGPT and Claude show under writ_browser_use and writ_record_website calls it to read the session's state and get one-time passes for the session's screencast and its take-over channel. The user watches the page in the card and can take it over there. It is not part of a conversation's work.
Inputs: session_id (required).
writ_browser_networkRead a session's network callsARead-onlyIdempotentInspect
Searches (operation=search, query, method) or reads in full (operation=detail, index) the backend requests the page made after capture_network: the site's real API. writ_browser_act api_call probes one with other values (a flow: several requests); an index feeds writ_browser_compose define_function from_index.
Inputs: session_id (required), index, query, method, +3 more.
writ_browser_saveSave a session as a workflowADestructiveInspect
Saves the open session as a replayable workflow and closes the browser, in the place its browser ran: the user's desktop library or Writ Cloud. Composed functions become callable API functions, declared inputs become its parameters. The answer carries the steps, the inputs and a run_example; the workflow runs at zero AI cost through writ_run_workflow. A save that references something no run could resolve is refused with the reasons, and the browser stays open.
Inputs: session_id (required), name, listing, save_to, +4 more.
writ_browser_sessionsList open browser sessionsBRead-onlyIdempotentInspect
Lists the account's open cloud browser sessions (each resumable by its session_id).
Inputs: limit, include_closed.
writ_browser_useOpen a browserADestructiveInspect
A REAL CLOUD BROWSER FOR A TASK ON A SITE: the user's signed-in account (a persona_id from writ_personas: the password stays sealed in Writ, and sessions never ask for a password), a click, form, submit or search inside an app, or a page a plain fetch cannot open (login wall, 403, CAPTCHA). Opens the browser and returns the first page; writ_browser_act drives it (Writ runs no model here). Recording is always on: writ_browser_save turns the session into a workflow that replays without a browser, writ_browser_cancel closes it (an open browser bills). The start answer carries the action vocabulary, the recording rules and, with a persona, the 2FA rules. NOT FOR: reading pages (writ_scrape). An API: writ_website_to_api opens this same browser, bound to a build.
Inputs: url (required), goal, auth_mode, fresh_exit, +5 more.
writ_crawl_filesList a crawl's captured filesCRead-onlyIdempotentInspect
The original files (PDFs, office documents, images, CSVs) a crawl captured, with short-lived download URLs.
Inputs: runs, crawl, limit, crawl_id.
writ_crawl_siteCrawl a site into a datasetADestructiveInspect
COLLECTS a site or a section into a queryable, change-tracked dataset (one row per page). Scope: intent (a section, in plain words), rank_cap=N (the top N items of a listing), seed_urls (known pages), or the whole site capped by page_budget. Modes: markdown (default, no AI), extract_mode='schema' (uniform records), executor='ai' + extract_prompt (per-page understanding, 5x the page rate). A bounded crawl answers with its rows; an open one returns a crawl_id for writ_crawl_status wait=true. NOT FOR: reading a few pages now (writ_scrape). Every option: writ_help('writ_crawl_site').
Inputs: url (required), name, wait, limit, +31 more.
writ_crawl_statusCheck a crawlBRead-onlyIdempotentInspect
Status of a crawl by crawl_id; wait=true holds up to 75 s and returns the collected rows when it converges.
Inputs: crawl_id (required), wait, limit, output, +2 more.
writ_create_automationCreate an automationBInspect
Creates an automation: on an event (a workflow or crawl completed, a monitor change, a webhook, a schedule) it runs a workflow, sends a notification templated over the event's data, and/or wakes an AI agent. Event, template and webhook options: writ_help('writ_create_automation').
Inputs: name (required), when, title, blocks, +21 more.
writ_create_http_extractionBuild an HTTP extractionBDestructiveInspect
Drafts or revises a multi-request browserless HTTP extraction (loops, GraphQL, cursor pagination) from captured requests and a plain-language goal. Every option: writ_help('writ_create_http_extraction').
Inputs: goal (required), apply, workflow, step_index, +5 more.
writ_create_monitorWatch a page for changesAInspect
WATCHES a page for changes: Writ checks it on a schedule and fires change_detected when the page, a CSS selector's text, a value read by extract, or a visual zone changes. Returns the monitor_id that writ_wire_monitor connects to an alert, a workflow or an AI task (a price watch takes a threshold there). Without interval the answer is needs_input: this plan's options and a tell_user for the user, nothing created. The page is read first: a sign-in answers needs_persona, a bot check offers use_residential.
Inputs: url (required), mode, watch, device, +13 more.
writ_devicesChoose a linked desktopBIdempotentInspect
The user's linked Writ desktops: list, use (scope this connection to one: runs, browsers, personas and monitors then target it), clear, monitors, datasets.
Inputs: action, device.
writ_diagnose_http_workflowDiagnose a workflow's HTTP laneBRead-onlyIdempotentInspect
Explains why a saved workflow's run returned nothing or failed: HTTP-lane readiness and, with task_id, the run's requests and responses.
Inputs: task_id, workflow, workflow_id.
writ_discovery_statusCheck an API buildARead-onlyIdempotentInspect
Status of a website-to-API build (a guided one, or one started in the Writ app). wait=true is one held call (up to 75 s) that follows the build to its newest rung and returns when it is done or parked. Answers: succeeded (workflow_id, functions, run_example), failed, cancelled, or needs_guidance (the build is the caller's to finish with writ_website_to_api build_id=; its map comes with it).
Inputs: build_id (required), wait, timeout_seconds.
writ_export_dataExport collected dataCRead-onlyIdempotentInspect
Exports a workflow's full data table as CSV or JSON.
Inputs: q, view, format, workflow, +1 more.
writ_expose_workflow_apiPublish a workflow as a REST APICIdempotentInspect
Publishes a saved workflow as a REST endpoint (a POST URL that waits and returns its JSON). Repeated calls reuse it.
Inputs: label, workflow, workflow_id, wait_timeout, +1 more.
writ_helpWrit tool referenceARead-onlyIdempotentInspect
The full reference of any Writ tool (every parameter and its rules) and the complete guide. topic = a tool name (e.g. 'writ_browser_compose', a 'run_' tool), 'guide' for the manual (recurring digests, HTTP flow building, buying on a price, crawl modes), 'actions' / 'recording' / '2fa' for the browser rules, 'http_flows' / 'flow_operators' for writing an HTTP flow, or empty for the list of topics.
Inputs: topic.
writ_list_webhooksList inbound webhook URLsBRead-onlyIdempotentInspect
The account's inbound webhook URLs and the automations they fire.
Inputs: webhook_trigger_id.
writ_list_workflowsList saved workflowsARead-onlyIdempotentInspect
Lists the workflows saved in the Writ account; each runs on demand without live browsing. Returns id, name, declared inputs (with input_rules: the values and format an input accepts), schedule, whether it is pinned as its own run_ tool, and, for an API with several functions, their names (functions, write_functions): call one with function_name.
Inputs: search.
writ_paymentPay with a card the user approvesBDestructiveInspect
Pays on a site with one of the user's cards; card numbers never reach this conversation. request (site, max_amount, purpose) returns a tell_user and an open_url where the user approves; wait (grant_id or confirmation_id); checkout pauses at the order button for the user's confirmation, then Writ places the order; fill; list (card handles only). Details: writ_help('writ_payment').
Inputs: action (required), site, steps, fields, +11 more.
writ_personasUse the user's saved sign-insAInspect
The user's own accounts on websites (personas): how Writ signs in as them. No password passes through this tool or the conversation, and its answers never ask for one: credentials are typed only into a Writ window. action='list' domain= shows the personas usable there; with none it answers persona_needed: a tell_user for the user, a create_url (a small Writ window with only the sign-in form, pre-filled for the site) and a link_id. action='wait' link_id= is one held call that answers when the user saves it, with its persona_id. Also get, request (a link for another account), sign_in (refresh the session) and record_login. A persona_id works on writ_scrape, writ_crawl_site, writ_browser_use and writ_run_workflow; a desktop persona ('device:...') signs in on that desktop, from its own vault.
Inputs: action (required), why, wait, force, +7 more.
writ_pin_workflow_toolPin a workflow as a toolCIdempotentInspect
Pins (or unpins) a saved workflow as its own run_ tool on this server.
Inputs: pinned, workflow, workflow_id.
writ_record_websiteRecord a website taskADestructiveInspect
Records a repeatable task on a site as a workflow (goal + start url): the same session as writ_browser_use, labelled with its goal, driven with writ_browser_act and saved with writ_browser_save. A goal that asks for an API opens as a writ_website_to_api build instead: the same browser, bound to the build.
Inputs: url (required), goal (required), device, auth_mode, +6 more.
writ_run_saved_crawlRun a saved crawlBInspect
Runs a saved crawl; max_age returns its recent data at no cost instead of re-crawling.
Inputs: crawl (required), wait, limit, output, +3 more.
writ_run_workflowRun a saved workflowADestructiveInspect
Runs a saved workflow by workflow_id or name and returns its extracted data (it waits by default). The answer's data is what the run returned and records_path names its records; pass output with only the fields the question needs (fields: ['price', 'data.date as date']) for a far smaller answer. Inputs go as top-level fields or under inputs; function_name runs one function of a multi-function API (with the sign-in it needs). max_age reuses a recent result at no cost. A write function previews with mutation_mode='dry_run'. Runs sign in as the workflow's persona or persona_id; no password is ever passed. Venue, network, files and output shape: writ_help('writ_run_workflow').
Inputs: wait, files, device, inputs, +13 more.
writ_saved_crawl_dataRead a saved crawl's dataBRead-onlyIdempotentInspect
Reads the data a saved crawl collected on its last completed run, without crawling.
Inputs: crawl (required), limit, output, preview_chars.
writ_saved_crawlsList saved crawlsBRead-onlyIdempotentInspect
Lists the crawls saved for re-running, with their scope.
Inputs: limit.
writ_scrapeRead web pagesAInspect
READ PAGES NOW, no browser session: one page (url), up to 20 pages in parallel (urls, on one site or several), or a listing plus its top N item pages (url + top_n). Returns clean markdown in 2-10 s, including pages a plain fetch cannot read: rendered by JavaScript (render_mode='browser'; a read that only got the page's shell says so and gives the retry), behind a bot wall or 403 (an automatic residential retry; render_mode='http' opens no browser, so it never passes a check), or behind the user's sign-in (persona_id). Discussion threads keep their comments. format='html' returns the raw HTML for selectors, for one page or a batch. A page that cannot be read says why (error.code, e.g. scrape_not_found: the URL does not exist on the site) and gives retry_with when another read can help. NOT FOR: a site-wide dataset (writ_crawl_site) or clicking and typing (writ_browser_use).
Inputs: url, urls, top_n, device, +8 more.
writ_search_dataSearch collected dataBRead-onlyIdempotentInspect
Searches everything the account's workflows already collected for a term, without running anything.
Inputs: q (required), limit, device, workflow, +2 more.
writ_set_scheduleSchedule a workflowCDestructiveIdempotentInspect
Schedules a saved workflow: every_minutes, or kind='daily'/'weekly' with time (HH:MM) and days. functions + inputs schedule chosen functions of a multi-function API.
Inputs: tz, days, kind, time, +7 more.
writ_update_saved_crawlEdit a saved crawlCDestructiveIdempotentInspect
Inspects or changes a saved crawl's settings in place.
Inputs: crawl (required), name, settings, description, +1 more.
writ_update_workflowEdit a saved workflowCDestructiveInspect
Inspects or edits a saved workflow: an outline, one function's source, targeted function or step edits, a settings patch. copy_to keeps a linked copy on Writ Cloud or the user's desktop. Every option: writ_help('writ_update_workflow').
Inputs: path, limit, patch, device, +18 more.
writ_website_to_apiTurn a website into an APIADestructiveInspect
TURNS A WEBSITE INTO A CALLABLE API (named functions with inputs, returning JSON), built by the caller in a real browser. url = the page that already shows the rows (search results or a listing, not the home page); goal = the inputs and fields wanted. The call first proposes the user's matching saved workflows and marketplace APIs (skip_existing / skip_marketplace build fresh), then opens a cloud browser bound to the build: capture_network records the site's own calls, writ_browser_network reads them, api_call probes them; a failed probe is evidence, not the end. Functions: HTTP flows first (writ_browser_compose define_function flow; writ_help('http_flows')), single requests (from_index) mixed in, DOM extraction last. writ_browser_save, then run_example on two inputs.
Inputs: url, goal, device, save_as, +9 more.
writ_wire_monitorConnect a monitor to an actionAInspect
Connects a monitor's change_detected event to an action: action='notify' (channels and recipients the account has configured), 'workflow' (runs a saved workflow), or 'ai_task' (an AI agent opens the page and works prompt). A price watch takes threshold (+ threshold_op): the action then runs once, when a check reads a price at or below it. Buying at a price (buy): writ_help('writ_wire_monitor').
Inputs: action (required), monitor_id (required), buy, name, +15 more.
writ_workflow_dataRead a workflow's collected dataCRead-onlyIdempotentInspect
Reads a saved workflow's collected data as a table: q filters, run_id picks one run, refs returns full records.
Inputs: q, refs, view, limit, +6 more.
writ_workflow_runsList workflow runsBRead-onlyIdempotentInspect
Run history (status, timing, errors, venue) of one workflow or all of them.
Inputs: limit, device, status, workflow, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Web scraping for agents. Point it at a URL and it returns the page as clean markdown, JavaScript-rendered pages included. Point it at a site and it maps the URLs or crawls the section you need in the background, a few pages at a time so results fit in the conversation. Search the web and read full pages, extract fields with a JSON schema you define (validated, never invented), read a store's catalogue or a blog's posts from the platform's own feed, and check whether a page has changed. Failed requests cost nothing. The free plan includes 1,500 credits a month.
Turn any public webpage into JSON with AI, save it as a live JSON API, and call it from your agent.
Websites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.
Cloud scraping & crawling API for AI agents. Turn any URL into clean, LLM-ready markdown.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceGives AI coding agents the web as an API: it scrapes pages to Markdown, crawls and maps sites, and runs ready-made or self-built skills for sites like Google Maps, Amazon, LinkedIn and Instagram, returning clean typed rows that repair themselves when a site changes. It also supports batched runs, scheduled workflows with apps like Slack and Sheets, saved logins, and Firecrawl/Apify-compatible endpoints.8MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to search the live web, fetch clean page content, extract schema-driven structured JSON, check link liveness, detect page changes, run recurring monitors, and verify claims against sources. It offers a free per-IP tier with no API key, plus pay-per-call or prepaid access for higher volume and LLM-backed tools.MIT
- FlicenseBqualityCmaintenanceCompiles any website into typed, callable tools for AI agents, enabling discovery and invocation of live web APIs and UI actions without custom MCP servers.81-
- FlicenseNot gradedqualityAmaintenanceEnables language models and AI assistants to scrape, extract, search, crawl, generate schemas, and monitor web data through an API-backed toolset.-
Glama MCP Gateway
Add one secure layer between your agents and this server.