Web2Actions
Web2Actions
将网站变成你的 AI 智能体可以使用的 MCP 服务器——无需 API。
Web2Actions 会观察网站的浏览器流量,逆向工程出网站真实的网络端点,并将它们打包成一组干净、命名的工具,供你的 AI 智能体通过 Model Context Protocol (MCP) 调用。无需公共 API。
工作原理
捕获 — 在网站上登录一次;浏览器流量会被记录。
生成 — 一个 LLM 将捕获的流量转换为连接器定义:干净、命名的工具,包含输入、输出和风险标签。
验证 — 每个工具都会针对实时网站进行冒烟测试。
服务 — 验证后的连接器作为标准 MCP 服务器暴露。
捕获是人工驱动的,而非自动的。 我们不会猜测每个按钮或替你点击网站。一个真实的浏览器会在你的机器上打开;你 登录并执行你想要变成工具的操作,我们记录这些流量。托管产品也遵循同样的理念——它是一个由你驱动的弹出式浏览器。CLI 只是为你运行那个浏览器。
Related MCP server: ApiTap
安装
pip install -e .命令
每个命令都是 web2actions <command> [options]。
model — 选择你的 LLM 提供商和模型(持久化)
web2actions model # show current
web2actions model google/gemini-2.5-flash # set default model (persisted)
web2actions model --provider openrouter # set default provider
web2actions model --alias sonnet=anthropic/claude-sonnet-4 # alias
web2actions model --aliases # list aliasescapture — 记录网站的流量
打开浏览器到该 URL,记录你登录和点击时产生的网络流量,然后写出一个 JSON 转储。
# Open the site; log in and click around manually; press Enter when done.
web2actions capture https://app.example.com
# Filter out analytics/static noise and save to a chosen file.
web2actions capture https://app.example.com --filter -o dump.json
# Automate a simple form login (fill + submit), then continue capturing.
web2actions capture https://app.example.com --login \
--username you@example.com --password "..." \
--username-selector "#username" --password-selector "#password" \
--submit-selector "#submit-btn" --success-indicator "#dashboard"选项:--login、--username、--password、--username-selector、--password-selector、--submit-selector、--success-indicator、--filter、--output/-o。
generate — 将捕获的流量转换为连接器定义
web2actions generate dump.json --model claude-sonnet-4 -o connector.json选项:--model(或 WEB2ACTIONS_MODEL 环境变量)、--output/-o。
validate — 根据模式检查连接器
web2actions validate connector.json
# -> VALIDserve — 将连接器作为 MCP 服务器暴露(stdio)
web2actions serve connector.json通过 stdio 将连接器连接到你的 AI 智能体的 MCP 客户端。
端到端示例
web2actions capture https://example.com --filter -o dump.json
web2actions generate dump.json --model claude-sonnet-4 -o connector.json
web2actions validate connector.json
web2actions serve connector.json从现有示例开始(无需捕获)
web2actions validate connector-spec/examples/simple-crm.json
web2actions serve connector-spec/examples/simple-crm.json自带 LLM(BYOK)
Web2Actions 使用 litellm,它通过一个 OpenAI 兼容接口连接到 100+ 提供商。你可以通过简单的命令选择提供商和模型——无需修改代码,并且该选择会在后续运行中记住。
支持的提供商
litellm 支持 100+ 提供商,包括 OpenAI、Anthropic、Google Gemini、OpenRouter、DeepSeek、Groq、xAI、Mistral、OpenAI 兼容的本地服务器(Ollama / llama.cpp / vLLM)、Bedrock、Azure 等。
每个提供商读取其标准的 API 密钥环境变量(例如 OPENAI_API_KEY、ANTHROPIC_API_KEY、GEMINI_API_KEY、OPENROUTER_API_KEY、DEEPSEEK_API_KEY、GROQ_API_KEY、XAI_API_KEY),或者对于本地服务器,根本不需要密钥。
用简单命令设置默认模型
# Pick a provider + model once; it is remembered (saved to ~/.web2actions/config.toml)
web2actions model openai/gpt-4o-mini
web2actions model anthropic/claude-sonnet-4
web2actions model gemini/gemini-2.5-flash
web2actions model openrouter/anthropic/claude-sonnet-4
web2actions model deepseek/deepseek-chat
# Show the current model
web2actions model
# Set a default provider
web2actions model --provider openrouter
# Add a short alias, then use it anywhere
web2actions model --alias sonnet=anthropic/claude-sonnet-4
web2actions generate dump.json --model sonnet
# List your aliases
web2actions model --aliases设置后,generate 会自动使用该模型:
web2actions model google/gemini-2.5-flash
export GEMINI_API_KEY=... # only needed the first time, per provider
web2actions generate dump.json # uses gemini-2.5-flash每次运行覆盖
传递 --model 以在单个命令中使用不同的提供商/模型,或设置 WEB2ACTIONS_MODEL 环境变量。优先级:--model > WEB2ACTIONS_MODEL > 已保存的配置。
web2actions generate dump.json --model openai/gpt-4o-mini如果未设置密钥
generate 会优雅地失败,并告诉你需要设置哪个密钥——它绝不会以原始堆栈跟踪崩溃。
仓库布局
connector-spec/— 连接器定义模式 + 验证器capture/— 浏览器会话 + 流量记录 + 噪声过滤generate/— LLM 提取(廉价路径)+ 沙盒回退validate/— 实时工具冒烟测试 + 风险标记mcp-runtime/— 提供任何连接器的共享 MCP 服务器cli/—web2actions命令行包装器
许可证
Apache-2.0。基于开源 CLI-Anything / CLI-Anything-Web 项目构建。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables real browser automation as tools in Cursor, Claude Desktop, Windsurf, and any MCP-compatible client, allowing AI agents to interact with web pages through natural language.24MIT
- AlicenseNot gradedqualityAmaintenanceMCP server that turns any website into an API by capturing or importing API endpoints, enabling AI agents to interact with web services without a browser, with 20-100x token cost reduction versus browser automation.159124Apache 2.0
- AlicenseNot gradedqualityCmaintenanceCaptures browser network traffic, analyzes API patterns, and exposes analysis tools through an MCP server for AI-assisted workflows.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to call web APIs extracted from HAR files, turning browser traffic into MCP tools.261MIT
Related MCP Connectors
Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.
Live browser debugging for AI assistants — DOM, console, network via MCP.
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rashidb0t/web2actions'
If you have feedback or need assistance with the MCP directory API, please join our Discord server