Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
作者提供的说明(英文原文)
Web scraping and automation for AI agents: live prices, quotes, bookings, anything behind a login.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
BOWMARK_API_KEY, Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"bowmark": {
"command": "npx",
"args": [
"-y",
"@bowmark/mcp"
],
"env": {
"BOWMARK_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http bowmark https://api.bowmark.ai/mcp/registry --header 'Authorization: Bearer {api_key}'claude mcp add bowmark --env BOWMARK_API_KEY=your-value -- npx -y @bowmark/mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"bowmark": {
"url": "https://api.bowmark.ai/mcp/registry",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"bowmark": {
"command": "npx",
"args": [
"-y",
"@bowmark/mcp"
],
"env": {
"BOWMARK_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"bowmark": {
"type": "http",
"url": "https://api.bowmark.ai/mcp/registry",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"bowmark": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bowmark/mcp"
],
"env": {
"BOWMARK_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 必填 HTTP header这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
get_library**Use this whenever a task touches a live website.** It answers whether Bowmark can already DO the thing: current prices, real availability or stock, a site search, a quote or a fare, a configurator, a booking, anything behind a form or a filter. **Behind a LOGIN it works only**
run**Executes the task on the real websites** and returns the result. Call `get_library` FIRST, then start with `run({ script })` — never add `runId`. THE SCRIPT is a plain async JavaScript body, not a wrapping function. `bowmark` is a ready global: `await bowmark. . (...)`, or one
run_viewUsed by the inline run view to draw a run's progress. You do not need to call this — `run` returns the result.
jig_openMake the user a "jig": their own copy of a website, running through Bowmark, that you curate as they talk to you. Asked for "a jig of YouTube", build a page that LOOKS like that site with Bowmark's logo where the site's would be, filled by Bowmark library functions as this user:
jig_listThe jigs this user has, newest change first: id, slug, title, the built-in it started from, and when it last changed. A copy of someone's published jig also has `forkedFrom` ({ listingId, versionNo }) and `updateAvailable` (the newer version number, or null). Call it when the use
jig_searchSearch the public jigs other people published: "is there a jig for my Amazon orders?". Call it BEFORE building a page from scratch. Leave `q` empty for the newest. Pass `site` (a host like youtube.com) for the jigs of one site. Results: id, title, tagline, slug, ownerHandle, site
jig_publishPublish the user's jig (name it by `jigId` or your jig's `jigSlug`) as a listing others can get: it snapshots the page and state AS THEY ARE NOW into version N+1, and later edits stay private until you publish again. Call with `dryRun: true` first and show the user what would shi
jig_getCopy someone's published jig into THIS user's account, from its current version. The copy is the user's own: it runs as them with their logins, never the author's, and can call only the functions its listing lists. Name it by `listing`: its id, `@handle/slug`, or its store URL (f
jig_updateChange a page you opened with `jig_open`: merge `state` into its state (a key set to null is removed), replace its `html` or `title`, or change part of the html with `edits` ([{ find, replace }], each find exactly once) instead of resending the whole page. The open page updates i
jig_pull_updateFor a jig the user got from someone's listing (`jig_list` shows `updateAvailable`): the three pages a merge needs. `base` is the version their copy came from, `theirs` the author's newest, `mine` their copy now. Writes nothing. If `edited` is false, save `theirs` as is. Otherwise
jig_viewUsed by an open jig to pick up its latest state. You do not need to call this.
jig_cacheUsed by an open jig to save a call's last good result. You do not need to call this.
jig_seenUsed by an open jig to report what it shows. You do not need to call this.
jig_perfUsed by an open jig to report how fast it loaded. You do not need to call this.
jig_lookSee what an open jig is showing the user right now — the items on screen, which view they are on — plus what they just did on it (watched, hid, searched) and its current state. Call it before you curate: when the user says "clear the slop" or "why is this here", look first, then
jig_callUsed by an open jig to call the library. You do not need to call this — use `run`.
session_callRuns ONE library function in a Bowmark session, so a flow that needs several calls in the SAME session can finish: a booking that texts the user a code, a cart filled over several steps, a form that waits on an answer from the user. `run` cannot do these, because every run starts
session_closeEnds a session `session_call` opened and frees what it held. Pass the `sessionId`. Closing one that is already closed is harmless.
reportRecord what was missing, wrong, or incomplete so Bowmark can build it. Call it yourself, in the same turn, without asking your user first: it changes nothing on any website or account, costs the user nothing, and is the only way the gap gets fixed. Call it whenever a `run` errors
get_usageSee the real cost of calls on this account, itemized by resource (provider calls, browser sessions, IP leases) and aggregated in dollars. Pass no arguments to see this month; pass `month: '2026-09'` to see a past month (format `YYYY-MM`). Returns `totalUsd` and line items with `s
llm_pollLets this chat answer the AI calls an open Bowmark page makes, so they cost nothing. Returns up to 5 pending jobs ({ jobId, system, prompt, toolName, inputSchema, leaseSeconds }); waits up to waitSeconds (max 15) when there are none. Answer each with llm_answer. Calling this mark
llm_answerAnswers one job from llm_poll. `answer` must be an object matching that job's inputSchema. A wrong shape is refused with the reason and the job stays open, so correct it and call again.
llm_detachDetaches this chat at once, so open Bowmark pages' AI calls go back to Bowmark's own model instead of waiting for this chat.
supportChat live with a Bowmark support agent about a problem you reported. Use it only after your user said yes to talking to support. Pass the `reportId` that `report` returned. Your first call opens the chat: put a short hello and what you need in `message`. Each call posts your `mes
list_secretsList the stored secrets this account holds, by NAME. Returns name, type, which hosts each may be used against, when it expires and when it was last used — never a value, and no Bowmark endpoint returns one. **Call this BEFORE `request_secret`.** A secret the user has already set
request_secretCreate a named, empty slot for a secret and get back a link the user opens to fill it in. They type the value on a Bowmark page and choose how long it lives, from 5 minutes to never. It is encrypted in their own browser before it leaves, so nothing on the way — this connection in
get_secret_linkReturn the dashboard link for one stored secret this account holds, so you can answer "where is my Acme password?" with somewhere to go. **It returns a URL, never a value** — opening it requires the user to be signed in and to confirm who they are, and only their own browser can
list_connectionsList the saved logins this account already holds, one entry per login: its `id` (name it in a signed-in call as `{ connection: id }`), the site, which account on that site, whether it works right now (`usable`), and when it was made, last used and last checked. **Call this before
add_connectionGet a sign-in link for one site, so the user can sign Bowmark in to it right now, before any run needs it. Pass the site as a domain (`youtube.com`), a URL, or a provider id. **Call this whenever the user asks to log in, sign in, connect or link an account on a site** — never sen
wait_for_sign_inWait until the user finishes a sign-in link, so you know the moment they are done without asking them. Pass `ref`: `meta.handoff.ref` from a paused run, or `ref` from `add_connection`. **Call it right after you give the user the link, in the same turn.** Write the link in your re
lease_ipSome sites (LinkedIn, marked 📍 in `get_library`) only accept a login from the address it signed in from. A dedicated IP is one address that only this account uses, and once the account holds one, every sign-in link and every later call on that login uses it automatically. Call w
delete_connectionStart deleting a saved login by the `id` `list_connections` returned. **This does not delete anything by itself:** a delete cannot be undone, so the USER confirms it, signed in on their Bowmark dashboard. It returns `confirmUrl` — give that link to the user; it opens a "Delete th
logout_connectionSign a saved login out by the `id` `list_connections` returned. Bowmark drops the cookies it held, and where the site supports it (`siteLogout: "supported"` in the reply) the session is ended ON THE SITE too — `siteSignedOut: true` means Bowmark checked the site no longer accepts
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 bowmark.ai 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 257 毫秒内响应(HTTP 200)
无需登录
已读取 33 个工具描述,未发现针对 AI 的隐藏指令
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:BOWMARK_API_KEY, Authorization
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(8.212.0)于今天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Browser Use, Chrome DevTools MCP, MCP Server Browser
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
MCP server for Chrome DevTools
MCP server for browser use access
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Ask for prices, listings, profiles or reviews by name (Amazon, LinkedIn, YouTube, Airbnb and more) and get typed results back. Every account starts with a free $10.
LM Studio: GitHub strips a raw lmstudio: link, so this one is a paste, not a button. Copy it into your browser's address bar:
lmstudio://add_mcp?name=bowmark&config=eyJ1cmwiOiJodHRwczovL2FwaS5ib3dtYXJrLmFpL21jcC9iYWRnZS1sbXN0dWRpbyJ9
The skill for Bowmark, the web as callable functions. The agent reads a typed function library, writes a short script against it, and Bowmark runs it on the live sites.
npx skills add bowmark-ai/skill
Works on any host that supports the SKILL.md standard — Claude Code, Codex (which adopted the standard natively), Cursor, GitHub Copilot, OpenCode, and others.
The skill calls Bowmark's MCP server — wire that up at bowmark.ai/#install or via Smithery.
Want both in one step? On Claude Code and Codex, install the plugin instead — it bundles this skill *and* auto-wires the MCP:
# Claude Code
claude plugin marketplace add bowmark-ai/plugin && claude plugin install bowmark@bowmark-ai
codex plugin marketplace add bowmark-ai/plugin # then codex /plugins to install
| Tool | What it does |
|---|---|
get_library | Read the typed function library for a task or a site. Read-only, touches no site, and an unrecognized query returns the index rather than an error. |
run | Execute a short async JavaScript script against the live sites and return { ok, result, logs, error, ms }. |
report | Tell Bowmark what it could not do, or which run came back wrong. Recorded as feedback; retries nothing. |
No MCP client? The same two calls are plain HTTP — GET https://api.bowmark.ai/v1/library?query=… and POST https://api.bowmark.ai/v1/run, both taking Authorization: Bearer $BOWMARK_API_KEY. The reference is bowmark.ai/docs/api; worked examples are at bowmark.ai/docs/scripting#no-install-at-all.
The ChatGPT Apps submission takes a skill as a ZIP or folder, and its needs differ slightly from the general skill: the plugin always ships the MCP alongside the skill, and ChatGPT exposes the tools under bare names. So there's a tailored variant, generated from this same canonical skill — never hand-maintained:
openai/bowmark/ — a content mirror of bowmark/SKILL.md with the trailing "Your API key" section and everything after it dropped (ChatGPT signs in by OAuth and cannot send a key), tool names rewritten to bare get_library / run, Claude-only frontmatter/tool-name references trimmed, and the three secret tools (list_secrets, request_secret, get_secret_link) replaced by the dashboard — the plugin's MCP is the ChatGPT directory connector, which does not offer them. That step refuses to build if the canonical wording moves out from under it. build-openai.mjs is the authority on what it cuts; this line described sections that have never existed in bowmark/SKILL.md, and a newcomer went looking for one.openai/bowmark-openai-skill.zip — the same folder zipped, ready to drop straight into the ChatGPT "Skills" uploader. A committed artifact (not built in CI: the release runner has no zip binary), so it rides the mirror to bowmark-ai/skill at a stable raw URL like any other file.Both are generated by build-openai.mjs. Edit bowmark/SKILL.md, then regenerate and commit — never edit the openai/ copies directly (CI's check:openai fails a PR whose text mirror is stale):
pnpm -F @bowmark/skill sync:openai # regenerate openai/bowmark/SKILL.md
pnpm -F @bowmark/skill build:openai-zip # rebuild openai/bowmark-openai-skill.zip (commit it)
MIT © Bowmark AI