AI 어시스턴트가 기록된 브라우저 워크플로우를 실행하고, 웹사이트를 크롤링하며, 웹 페이지를 호출 가능한 API로 변환할 수 있도록 지원합니다.
다른 이름 usewrit/writ-mcp, writ-mcp
- 스타
- 1
- Tools
- 32
- 다운로드, 30일
- 211
- 최신 버전
- 1.0.0
- 마지막 커밋
- 2026년 10월 10일
- 라이선스
- MIT
Writ Cloud MCP란?
AI 어시스턴트가 기록된 브라우저 워크플로우를 실행하고, 웹사이트를 크롤링하며, 웹 페이지를 호출 가능한 API로 변환할 수 있도록 지원합니다. 32개 도구를 제공합니다. 예: writ_list_workflows, writ_run_workflow, writ_pin_workflow_tool.
프로젝트 README에서 생성된 요약
Writ Cloud MCP server 정보
Writ Cloud는 Claude Desktop, Cursor, Windsurf와 같은 MCP 클라이언트를 Writ 생태계에 연결하는 투명 프록시 역할을 합니다. 이를 통해 AI 어시스턴트는 기록된 브라우저 워크플로우와 상호작용하고, 웹사이트 크롤링을 수행하며, 웹 페이지를 호출 가능한 REST API로 변환할 수 있습니다. 개발자는 이 서버를 사용하여 수동 브라우저 작업을 어시스턴트가 실행, 관리 및 예약할 수 있는 자동화 도구로 전환할 수 있습니다.
사용자는 환경 변수를 통해 Writ API key와 coordinator URL을 제공하여 연결합니다. 기본적으로 Writ Cloud를 사용하지만, 셀프 호스팅된 coordinator도 지원합니다. 이 서버는 작업 실행을 위한 writ_run_workflow, 마크다운 콘텐츠 읽기를 위한 writ_scrape, 분산 사이트 크롤링을 위한 writ_crawl_site 등 다양한 도구를 제공합니다. 의존성 없이 Node core만을 사용하는 경량 설계로 제작되어, Writ 백엔드에 새로운 도구가 추가되면 패키지 업데이트 없이도 어시스턴트에서 즉시 사용할 수 있습니다.
활용 사례
- 1기록된 브라우저 작업 실행AI 어시스턴트가 특정 저장된 워크플로우를 실행하여 웹사이트에서 데이터를 추출할 수 있습니다.
- 2인증된 웹 세션 관리어시스턴트가 저장된 identity를 사용하여 로그인이나 2단계 인증이 필요한 웹사이트에 접속할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
Writ Cloud MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 Writ Cloud MCP 설치
$ claude mcp add --env 'WRIT_API_KEY=<YOUR_WRIT_API_KEY>' writ-mcp -- npx -y writ-mcpCursor에 Writ Cloud MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"writ-mcp": {
"command": "npx",
"args": [
"-y",
"writ-mcp"
],
"env": {
"WRIT_API_KEY": "<YOUR_WRIT_API_KEY>"
}
}
}
}VS Code에 Writ Cloud MCP 설치
.vscode/mcp.json
{
"servers": {
"writ-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"writ-mcp"
],
"env": {
"WRIT_API_KEY": "<YOUR_WRIT_API_KEY>"
}
}
}
}VS Code CLI에 Writ Cloud MCP 설치
$ code --add-mcp '{"name":"writ-mcp","type":"stdio","command":"npx","args":["-y","writ-mcp"],"env":{"WRIT_API_KEY":"<YOUR_WRIT_API_KEY>"}}'Claude Desktop에 Writ Cloud MCP 설치
claude_desktop_config.json
{
"mcpServers": {
"writ-mcp": {
"command": "npx",
"args": [
"-y",
"writ-mcp"
],
"env": {
"WRIT_API_KEY": "<YOUR_WRIT_API_KEY>"
}
}
}
}Codex에 Writ Cloud MCP 설치
$ codex mcp add writ-mcp --env 'WRIT_API_KEY=<YOUR_WRIT_API_KEY>' -- npx -y writ-mcpCodex config.toml에 Writ Cloud MCP 설치
~/.codex/config.toml
[mcp_servers.writ-mcp] command = "npx" args = ["-y", "writ-mcp"] [mcp_servers.writ-mcp.env] WRIT_API_KEY = "<YOUR_WRIT_API_KEY>"
Gemini CLI에 Writ Cloud MCP 설치
$ gemini mcp add -s user -e 'WRIT_API_KEY=<YOUR_WRIT_API_KEY>' writ-mcp npx -- -y writ-mcpGemini settings.json에 Writ Cloud MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"writ-mcp": {
"command": "npx",
"args": [
"-y",
"writ-mcp"
],
"env": {
"WRIT_API_KEY": "<YOUR_WRIT_API_KEY>"
}
}
}
}Writ Cloud MCP 도구 32
README에서 감지됨writ_list_workflowswrit_run_workflowwrit_pin_workflow_toolwrit_update_workflowwrit_diagnose_http_workflowwrit_create_http_extractionwrit_workflow_datawrit_search_datawrit_export_datawrit_workflow_runswrit_set_schedulewrit_expose_workflow_api
| writ_list_workflows | — | |
| writ_run_workflow | — | |
| writ_pin_workflow_tool | — | |
| writ_update_workflow | — | |
| writ_diagnose_http_workflow | — | |
| writ_create_http_extraction | — | |
| writ_workflow_data | — | |
| writ_search_data | — | |
| writ_export_data | — | |
| writ_workflow_runs | — | |
| writ_set_schedule | — | |
| writ_expose_workflow_api | — |
도구 32개 모두 보기도구 수 줄이기
writ_scrapewrit_crawl_fileswrit_update_saved_crawlwrit_personaswrit_paymentwrit_deviceswrit_create_automationwrit_list_webhookswrit_browser_usewrit_record_websitewrit_website_to_apiwrit_discovery_statuswrit_browser_composewrit_browser_ask_userwrit_browser_sessionshitmisswrit_saved_crawlswrit_run_saved_crawlwrit_saved_crawl_data
| writ_scrape | — | |
| writ_crawl_files | — | |
| writ_update_saved_crawl | — | |
| writ_personas | — | |
| writ_payment | — | |
| writ_devices | — | |
| writ_create_automation | — | |
| writ_list_webhooks | — | |
| writ_browser_use | — | |
| writ_record_website | — | |
| writ_website_to_api | — | |
| writ_discovery_status | — | |
| writ_browser_compose | — | |
| writ_browser_ask_user | — | |
| writ_browser_sessions | — | |
| hit | — | |
| miss | — | |
| writ_saved_crawls | — | |
| writ_run_saved_crawl | — | |
| writ_saved_crawl_data | — |
구성
WRIT_API_KEY필수비밀A Writ API key with the mcp scope (Settings -> Developers).
WRIT_COORDINATOR_URL
| 이름 | 설명 | 유형 |
|---|---|---|
| WRIT_API_KEY | A Writ API key with the mcp scope (Settings -> Developers). | 필수비밀 |
| WRIT_COORDINATOR_URL | — |
자동 검사
2026년 11월 12일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 이는 보안 감사가 아닙니다. 코드를 직접 읽고 서버에 필요한 최소한의 권한만 부여하십시오. 검사 방식
- 소스 저장소 연결 및 접근 가능통과
- 오픈 소스 라이선스 (OSI)통과
- 최근 1년 내 커밋 또는 릴리스통과
- 패키지 이름이 인기 패키지와 유사하지 않음통과
- 원격 엔드포인트가 HTTPS 사용통과
- 파괴적인 도구에 라벨 표시됨통과
- 모델에 대한 숨겨진 지침 없음통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음통과
README
GitHub에서 보기writ-mcp connects a stdio MCP client — Claude Code, Claude Desktop, Cursor, Windsurf, Codex — to Writ, so the browser workflows you already recorded become tools your assistant can call: run them, read the data they collected, search past results, schedule them, expose them as REST endpoints, and kick off site crawls.
It is a transparent stdio↔HTTP proxy and nothing else. Every tool, schema and rule lives server-side, so what you get always matches what your instance can do — and a new tool never requires upgrading this package. Zero dependencies, one file, Node core only.
Clients that speak Streamable HTTP natively don't need this at all — point them straight at the
/mcpendpoint with anAuthorization: Bearer <key>header.
Quick start
1. Get an API key. In the Writ app: Settings → Developers → API keys. Keys
look like wt_….
2. Add the server.
Against a self-hosted coordinator:
claude mcp add writ-selfhost -e WRIT_API_KEY=<YOUR_API_KEY> -- npx -y writ-mcp --url https://writ.example.com
Against a coordinator on this machine:
claude mcp add writ-selfhost -e WRIT_API_KEY=<YOUR_API_KEY> -- npx -y writ-mcp --url http://localhost:8000
Against a published per-workflow endpoint (an "Expose as MCP" slug URL is used verbatim — no path rewriting):
claude mcp add my-tools -e WRIT_API_KEY=<YOUR_API_KEY> -- npx -y writ-mcp --url https://mcp.example.com/mcp/my-tools
3. Check it.
claude mcp list
Writ Cloud is the default target when you pass no
--url(https://api.usewrit.app). Pass--urlto point the connector at your own coordinator instead. See Status.
Pass the key through the environment, not the command line.
--api-keyworks, but it puts your key in the process's argument list where any local process can read it viaps, and your shell records it in history. The connector prints a note when you use it.
Your running coordinator also hands out these one-liners, pre-filled, on its
Connect page and at GET /api/mcp/connect-info:
Claude Desktop / Cursor (config file)
Add to claude_desktop_config.json (Claude Desktop) or ~/.cursor/mcp.json
(Cursor). The env form is recommended — it keeps the key out of the argument
list:
{
"mcpServers": {
"writ-selfhost": {
"command": "npx",
"args": ["-y", "writ-mcp"],
"env": {
"WRIT_COORDINATOR_URL": "https://writ.example.com",
"WRIT_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
Without npm
A self-host install bundles this connector at connectors/writ-mcp. There is no
build step, so you can run it straight from disk:
node /path/to/writ/connectors/writ-mcp/index.js --url https://writ.example.com
It coexists with the other Writ servers. Each surface registers under its own slug on purpose — the desktop app is
writ, Writ Cloud iswrit-cloud, a self-hosted coordinator iswrit-selfhost— and each identifies itself to the assistant with a distinct title. Keep any combination connected at once.
Tools you get
Served by the server you connect to, not by this package, so a new server tool reaches you without a connector update. Writ Cloud lists the 39 tools below; a self-hosted coordinator lists the ones marked in its column.
| Tool | What it does | Writ Cloud | Self-hosted |
|---|---|---|---|
writ_list_workflows |
Your saved workflows (a run_<name> tool is added only for workflows you pin) |
yes | yes |
writ_run_workflow |
Run one and wait for the extracted data | yes | yes |
writ_pin_workflow_tool |
Pin or unpin a workflow as its own run_<name> tool — off by default, capped; everything still runs via writ_run_workflow |
yes | yes |
writ_update_workflow |
Read a workflow's outline or edit it in place (settings, steps, functions, its agent skill) | yes | yes |
writ_diagnose_http_workflow |
Show what every request of a run was answered with, and whether it ran without a browser | yes | no |
writ_create_http_extraction |
Author a multi-request browserless extraction from captured requests | yes | no |
writ_workflow_data |
Read a workflow's accumulated data table | yes | yes |
writ_search_data |
Search across everything already collected | yes | yes |
writ_export_data |
Export a workflow's data as CSV/JSON | yes | yes |
writ_workflow_runs |
Run history and status | yes | yes |
writ_set_schedule |
Schedule a workflow (interval / daily / weekly) | yes | yes |
writ_expose_workflow_api |
Publish a workflow as a callable REST endpoint | yes | yes |
writ_scrape |
Read a page, or several, as clean markdown (Cloud also reads a listing's top N) | yes | yes |
writ_crawl_site / writ_crawl_status |
Start and poll a distributed site crawl | yes | yes |
writ_crawl_files |
The original documents a crawl captured (PDFs, office files, images) | yes | no |
writ_saved_crawls / writ_run_saved_crawl / writ_saved_crawl_data |
Saved crawls (see below) | yes | yes |
writ_update_saved_crawl |
Inspect or change a saved crawl's settings | yes | no |
writ_personas |
See your saved sign-in identities and get them ready (see below) | yes | yes |
writ_payment |
Pay with a card the user approves; Writ places the order once they confirm | yes | no |
writ_devices |
Your linked Writ desktops: list them, or point this connection at one | yes | no |
writ_create_automation |
Event or clock → run a workflow, notify, or wake an agent | yes | yes |
writ_list_webhooks |
Your inbound webhook URLs and the automations they fire | yes | yes |
writ_create_monitor / writ_wire_monitor |
Watch a page and react to changes | yes | yes |
writ_browser_use |
Open a real browser your assistant drives turn by turn | yes | yes |
writ_record_website |
Record a repeatable task as a workflow | yes | yes |
writ_website_to_api |
Turn a website into a callable API | yes | yes |
writ_discovery_status |
Follow an API build to its result | yes | no |
writ_browser_act / _context / _network / _save / _cancel |
Act in the browser, read the page and its network calls, save or close the session | yes | yes |
writ_browser_compose |
Define named functions, inputs and explicit steps in a session | yes | no |
writ_browser_ask_user |
Hand a CAPTCHA, a code or a decision to the user in the live browser | yes | no |
writ_browser_sessions |
Open browser sessions you can resume | yes | no |
writ_record_start / _act / _context / _network / _save / _cancel |
Older names of the browser loop, kept for compatibility | no | yes |
The build tools (writ_browser_use, writ_record_website, writ_website_to_api, then
writ_browser_act / _context / _network / _save / _cancel) are on both targets;
neither has a writ_build tool, so use writ_record_website. Your
assistant opens a real browser, drives it turn by turn, and saves the session as
a reusable workflow that afterwards replays with no model in the loop. Writ Cloud
runs it on Writ's fleet; a self-hosted coordinator runs it on your own fleet
agent. Either way your assistant is the
brain — no second model key is involved.
Reusing a recent result (max_age)
Running a workflow drives a real browser, so asking the same question twice in one
session costs two full runs and two waits. Every workflow tool takes an optional
max_age (seconds) meaning a recent answer is good enough:
{ "name": "run_price_check", "arguments": { "sku": "B0C123", "max_age": 300 } }
- omitted or
0— always run fresh (the default; nothing goes stale on its own). N— reuse a result younger thanNseconds, otherwise run.
A reused answer carries _cache: {hit: true, age_seconds: N} so the assistant can
tell how current it is.
max_age works identically against Writ Cloud and a self-hosted coordinator, and on
a pinned workflow's own run_<name> tool as well as writ_run_workflow.
Calling a saved crawl (writ_run_saved_crawl)
A whole-site crawl is slow and metered, so re-crawling to answer the same question is
the most expensive mistake an assistant can make. A saved crawl is a stored crawl
configuration with a stable name, and the same max_age contract applies to it:
{ "name": "writ_run_saved_crawl", "arguments": { "crawl": "docs", "max_age": 86400 } }
- hit — the pages that crawl already collected come back inline, instantly, with nothing crawled and nothing metered.
- miss — the site is crawled again with the saved settings, and you get a crawl
id to poll with
writ_crawl_status(a crawl outlives a single tool call).
Three tools cover the surface:
| Tool | What it does |
|---|---|
writ_saved_crawls |
List saved crawls. Check here before crawling a site again. |
writ_run_saved_crawl |
Run one, reusing recent data when max_age allows. |
writ_saved_crawl_data |
Read what one already collected, at any age. Never crawls. |
To create one, pass save_as to writ_crawl_site — that saves the settings and
runs them, so the crawl becomes callable by REST as well. Re-using the same save_as
updates that saved crawl instead of piling up duplicates. Saving needs an
admin-scoped credential (it creates reusable, callable configuration); running one
needs only run.
Sites behind a login (writ_personas)
A persona is a saved sign-in identity — username, credentials sealed
server-side, optional 2FA, and a warm signed-in session. writ_personas lists
yours (with per-persona readiness), inspects one (get), refreshes its session
by running its login workflow (sign_in), or has the AI record the sign-in flow
once so the persona can sign itself in from then on (record_login). The
assistant then passes a persona_id to writ_run_workflow (and each pinned
run_<name> tool), writ_crawl_site, or writ_scrape — plus writ_browser_use
on Writ Cloud — and the task runs signed in, with 2FA codes minted server-side.
By design the connector can only use personas, never manage them: creating, editing or deleting one involves credentials, and no credential or one-time code ever crosses the MCP connection in either direction. Personas are created in the Writ dashboard.
If a tool call times out
It comes back as status: "running" with retryable: true. The run was not
cancelled — calling the tool again starts a second run. Wait, then retry with a
max_age wide enough to pick up the first run's result once it lands.
Configuration
Flags take precedence over environment variables.
| Flag | Env | Default | Purpose |
|---|---|---|---|
--url |
WRIT_COORDINATOR_URL / WRIT_URL |
https://api.usewrit.app |
Target base URL. A URL whose path is already /mcp or /mcp/<slug> is used verbatim. |
--api-key |
WRIT_API_KEY |
— (required) | Key for Authorization: Bearer. Prefer the env var. |
--insecure |
WRIT_INSECURE_TLS=1 |
off | Accept a self-signed local-CA cert. Private networks only. |
--timeout |
WRIT_MCP_TIMEOUT_MS |
600000 |
Per-request timeout (ms); covers long writ_run_workflow waits. |
--help / --version |
— | — | Print usage or version and exit. |
HTTPS with a local CA (self-host): trust the CA (recommended) and use the
https://address, or setNODE_EXTRA_CA_CERTS=/path/to/ca.pem. Use--insecureonly for localhost testing — it disables certificate verification entirely, which exposes your key to a man-in-the-middle.
Security
This process exists to carry a credential, so everything that could expose one is
made loud rather than convenient. Full detail in SECURITY.md.
- The key goes to
--urland nowhere else. No telemetry, no analytics, no update check. Zero dependencies means there is no transitive code in the process that could phone home — and CI fails the build if that ever changes. - Redirects are never followed. Replaying your
Authorizationheader to whatever origin aLocationheader names would hand your key to a host you didn't choose. A 3xx becomes an error telling you to point--urlat the final URL. - Credentials in a URL are redacted from every diagnostic. MCP clients write a
server's stderr to a log file on disk;
https://user:pass@host/would otherwise be written down in plaintext. - Loud warnings, on stderr, for every way a key leaks: TLS verification
disabled, plaintext
http://to a non-loopback host, or a key passed on the command line. - Retries never double-run a workflow. Only read-only methods are retried;
tools/callis sent exactly once, because a retry could re-execute a side effect the connector cannot see. - Responses are bounded at 32 MB, so a broken endpoint can't grow this process until the OS kills your session.
- No request is ever left unanswered — a hung MCP client is a denial of service on your assistant, and that is the failure this connector works hardest to make impossible.
Scope your keys. Give a key only workflows:read / workflows:execute unless
a tool you actually use needs more.
Verifying what you install
Releases are published from CI with npm provenance, so the tarball is cryptographically linked to the commit and workflow that built it:
npm audit signatures
Troubleshooting
| Symptom | Cause and fix |
|---|---|
Unauthorized: … rejected the API key |
The key is wrong, disabled, or lacks scope. Recreate it under Settings → Developers with workflows:read / workflows:execute. |
Cannot reach … |
Wrong --url, or the target is down. For a self-signed cert see the local-CA note above. |
… redirected (HTTP 301) |
Your reverse proxy redirects (usually http → https). Point --url at the final URL. |
The API key contains characters that cannot be sent in an HTTP header |
A newline or control character got into the key — usually a copy-paste artifact. Re-copy it. |
| No tools listed | The connector could not reach the coordinator, or the key was rejected — see the rows above. With a working connection the static writ_* tools are always listed, even before you save a workflow. |
A workflow has no run_<name> tool |
Derived tools are opt-in and off by default. Pin the workflow with writ_pin_workflow_tool (or the app's Expose as MCP tool switch) and it appears on the next tools/list, up to 20 per account. Every workflow runs through writ_run_workflow either way. |
| Client won't connect, no error | Read the connector's stderr — your client logs it. Claude Code: ~/Library/Caches/claude-cli-nodejs/<project>/mcp-logs-<name>/. |
Status
| Self-hosted coordinator | Supported and verified end to end. |
Published /mcp/<slug> endpoints |
Supported. |
Writ Cloud (https://api.usewrit.app, the no---url default) |
Supported. Used automatically when no --url is passed. |
Development
npm test
No dev dependencies — the suite uses Node's built-in node:test and drives the
real index.js as a subprocess against a mock MCP server, exercising the same
stdio path an MCP client uses. It runs in about six seconds. npm publish runs it
automatically via prepublishOnly.
See CONTRIBUTING.md — note the two hard rules: zero
dependencies, permanently, and no tool logic here.
The rest of Writ
| usewrit/writ | The self-host coordinator — web UI, API, your data. Start here. |
| usewrit/writ-agent | The Rust fleet worker that does the actual browsing. |
| writ-mcp (this repo) | The MCP connector. |
License
MIT — see LICENSE.
This package is deliberately permissive because it runs inside your MCP client, not inside the coordinator, so it has to be embeddable anywhere. The coordinator it talks to is AGPL-3.0-only; the two licenses are not interchangeable.
Writ Cloud MCP 질문
Writ Cloud MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add --env 'WRIT_API_KEY=<YOUR_WRIT_API_KEY>' writ-mcp -- npx -y writ-mcp를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
Writ Cloud MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
Writ Cloud MCP는 어떤 도구를 제공하나요?
32개 도구를 제공합니다. 예: writ_list_workflows, writ_run_workflow, writ_pin_workflow_tool, writ_update_workflow, writ_diagnose_http_workflow.
Writ Cloud란 무엇인가요?
Writ Cloud는 어시스턴트가 저장된 브라우저 워크플로우를 실행하고, 수집된 데이터를 읽고, 과거 검색 결과를 탐색하며, 사이트 크롤링을 수행할 수 있도록 지원하는 서비스입니다.
로그인이 필요한 사이트에서도 사용할 수 있나요?
네, 자격 증명과 로그인 세션이 포함된 저장된 로그인 정보인 'personas'를 사용하여 사용할 수 있습니다.
웹사이트의 불필요한 재크롤링을 방지하려면 어떻게 하나요?
워크플로우 도구에서 'max_age' 인자를 사용하여 최근 결과를 재사용하거나, 'saved crawls'를 사용하여 이전에 수집된 데이터를 재사용할 수 있습니다.