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)
Real Chrome profiles with site intelligence — already logged in, PII anonymization, sessions persist
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。
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"pagerunner": {
"command": "npx",
"args": [
"-y",
"pagerunner"
]
}
}
}在终端中运行这条命令
claude mcp add pagerunner -- npx -y pagerunner粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"pagerunner": {
"command": "npx",
"args": [
"-y",
"pagerunner"
]
}
}
}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": {
"pagerunner": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pagerunner"
]
}
}
}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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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7日
注册名称已通过 GitHub 账户 Enreign 验证,该账户拥有此仓库
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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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 1 项适用的基础检查中通过了 1 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。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.8.0)于7个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
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。
A Chrome browser automation MCP server. Connect Claude (or any MCP client) to a real Chrome session — using your existing profiles with their cookies, saved passwords, and history.
[!WARNING]
Pagerunner is early-stage software (v0.x). APIs and configuration formats may change between releases.
Pagerunner launches Chrome with your existing user profile via CDP (Chrome DevTools Protocol) and exposes it as an MCP server over stdin/stdout. Claude can then navigate, click, type, screenshot, and run JavaScript in the live browser.
1. Install
# Option A — Homebrew (easiest on macOS/Linux):
brew tap enreign/pagerunner brew install pagerunner
cargo install pagerunner
curl -L https://github.com/Enreign/pagerunner/releases/latest/download/pagerunner-macos-arm64 \ -o pagerunner && chmod +x pagerunner
curl -L https://github.com/Enreign/pagerunner/releases/latest/download/pagerunner-macos-x86_64 \ -o pagerunner && chmod +x pagerunner
curl -L https://github.com/Enreign/pagerunner/releases/latest/download/pagerunner-linux-x86_64 \ -o pagerunner && chmod +x pagerunner
xattr -d com.apple.quarantine pagerunner
cargo install --git https://github.com/Enreign/pagerunner --locked
cargo build --release
2. Auto-detect Chrome profiles
pagerunner init
This reads Chrome's profile list and writes ~/.pagerunner/config.toml automatically. Run pagerunner status to verify.
Alternatively, write ~/.pagerunner/config.toml by hand — see pagerunner example-config for the format.
3. Register as MCP server
# If installed (Options A or B — binary is in PATH):
claude mcp add pagerunner "$(which pagerunner)" mcp
claude mcp add pagerunner "$(pwd)/target/release/pagerunner" mcp
For Claude Desktop, add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": { "pagerunner": { "command": "/absolute/path/to/pagerunner", "args": ["mcp"] } } }
Note: The
mcpsubcommand is required — registering just the binary path withoutmcpwill not work.
Note: Chrome locks profile directories. Close any Chrome window using a profile before opening a Pagerunner session on it.
4. Set up in your project (optional)
In any project directory with a CLAUDE.md or AGENTS.md:
pagerunner init
Pagerunner prints a ready-to-use usage snippet and offers to append it to your project file automatically. For scripting: pagerunner init --json.
5. (Optional, `--features ner` builds only) Download the NER model
pagerunner download-model # ~65MB, enables PERSON/ORG name detection
Copy the example agent instructions into your project root so Claude (or any agent) immediately knows how to use Pagerunner:
# Claude Code projects:
curl -sL https://raw.githubusercontent.com/Enreign/pagerunner/main/docs/examples/CLAUDE.md -o CLAUDE.md
curl -sL https://raw.githubusercontent.com/Enreign/pagerunner/main/docs/examples/AGENTS.md -o AGENTS.md
Or paste the content manually and extend it with project-specific instructions.
For comprehensive guidance, workflows, and examples tailored to 4 different use cases, install the Pagerunner Skill:
# Install the skill (once available in skills.sh registry)
claude skill install pagerunner-skill
Or explore the skill repository directly: pagerunner-skill
The skill includes:
Start with the skill's SKILL.md to find your use case and quick start path.
| Tool | Description |
|---|---|
list_profiles | List configured Chrome profiles |
open_session | Launch Chrome for a profile, returns session_id |
attach_session | Attach to an existing Chrome instance via --remote-debugging-port |
close_session | Kill a Chrome session |
list_sessions | List active sessions |
list_tabs | List open tabs in a session |
new_tab | Open a new tab, returns target_id |
close_tab | Close a specific tab |
| Tool | Description |
|---|---|
navigate | Navigate a tab to a URL |
wait_for | Wait for a CSS selector, URL pattern, or fixed delay |
get_content | Get visible text content of a tab |
screenshot | Capture a tab as PNG (saved to temp file or inline base64) |
evaluate | Run JavaScript in a tab, returns the result |
| Tool | Description |
|---|---|
click | Click an element by CSS selector |
type_text | Type text at the focused element or a given selector |
fill | Set input value with React/Vue/Angular synthetic events |
select | Choose a dropdown option by value |
scroll | Scroll the page by pixels or scroll an element into view |
| Tool | Description |
|---|---|
save_snapshot | Save current page cookies/localStorage to the encrypted DB |
restore_snapshot | Restore a saved snapshot into the current tab |
list_snapshots | List saved snapshots (optionally across all profiles) |
delete_snapshot | Delete a saved snapshot |
save_tab_state | Save all open tab URLs to the DB |
restore_tab_state | Reopen the previously saved tabs |
| Tool | Description |
|---|---|
kv_set | Store a value in a persistent namespace |
kv_get | Retrieve a value by key |
kv_delete | Delete a key |
kv_list | List keys in a namespace (with optional prefix filter) |
kv_clear | Delete all keys in a namespace |
| Tool | Description |
|---|---|
get_network_log | Inspect HTTP requests captured in a session |
get_console_log | Capture JavaScript console output from a tab |
| Tool | Description |
|---|---|
get_site_knowledge | Inspect what Pagerunner has learned about a site (adapters, auth tokens, selector health) |
register_adapter | Store a JS adapter for direct API calls against a site |
call_site_api | Execute a stored adapter in the browser tab |
generate_adapter | Auto-generate a JS adapter from network traffic using Claude (requires ANTHROPIC_API_KEY) |
| Tool | Description |
|---|---|
save_session_checkpoint | Save full tab state (URLs + scroll positions) for all tabs in a session |
restore_session_checkpoint | Reopen all saved tabs and navigate to stored URLs |
list_session_checkpoints | List saved checkpoints for a profile |
delete_session_checkpoint | Remove a checkpoint by ID |
Pagerunner learns about sites as you use them and can call site APIs directly using your session credentials — no separate auth setup required.
Adapters are short JS functions stored in the encrypted DB and executed in the browser tab. Use them to call APIs that a site exposes (typically the same API the web UI uses):
register_adapter(origin="https://github.com", name="list-issues",
description="List open issues for a repo", js_code="async ({owner, repo}) => { const r = await fetch(...); return r.json() }")
call_site_api(session_id, target_id, origin="https://github.com", name="list-issues", params={"owner": "Enreign", "repo": "pagerunner"})
Seed adapters for GitHub, Linear, Jira, Notion, and Gmail are built in.
Auth token detection — Bearer tokens, API keys, and session cookies discovered in network traffic are stored in the encrypted site vault. Adapters automatically have access to them via the credentials argument.
Selector stability — click, fill, and select track success/failure rates per selector. A fragility warning appears in the tool response when a selector fails >30% of the time over ≥5 uses.
Save complete browser state (all open tabs with URLs and scroll positions) and restore it in any future session:
save_session_checkpoint(session_id, name="before-review")
→ checkpoint_id: cp_abc123
restore_session_checkpoint(session_id, checkpoint_id="cp_abc123") → reopens all saved tabs at their stored URLs
Checkpoints are stored in the encrypted DB and scoped to a profile.
A native Swift companion app lives at apps/menubar/. It shows all Chrome profiles, active sessions, open tabs, and daemon status from the menu bar — no terminal required.
Features:
Build and run:
pagerunner daemon &
cd apps/menubar bash scripts/package.sh # builds + bundles into scripts/Pagerunner.app open scripts/Pagerunner.app
Pass anonymize: true to open_session to strip PII from all get_content and evaluate results before they reach Claude. Screenshots are blocked in anonymization mode.
{ "tool": "open_session", "profile": "personal", "anonymize": true }
Detected by default: EMAIL, PHONE, CREDIT_CARD, IBAN, SSN, IP With `--features ner` build: also detects PERSON and ORG names via a local ONNX model
[EMAIL:a3f9b2]. Pass tokens back to fill/type_text — Pagerunner de-tokenizes before writing to the DOM.[EMAIL] — no vault, no de-tokenization.# 1. Build with NER support:
cargo build --release --features ner
只显示了开头部分;其余内容请在仓库中阅读