webmcpThis skill should be used when browsing or automating web pages that expose tools via the WebMCP API (window.navigator.modelContext). It teaches agents how to discover, inspect, and invoke WebMCP tools on websites instead of relying on DOM scraping or UI actuation.
Install via ClawdBot CLI:
clawdbot install brunobuddy/webmcpGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/webmachinelearning/webmcpAudited Apr 16, 2026 · audit v1.0
Generated Mar 1, 2026
An AI agent can use WebMCP tools to add products to a shopping cart, apply discount codes, or complete checkout steps on e-commerce sites that expose these functions. This avoids fragile DOM scraping of dynamic product pages and ensures reliable cart updates even during SPA navigation.
On banking or investment platforms, an agent can invoke WebMCP tools to fetch portfolio summaries, execute trades with user confirmation, or generate reports. This provides structured access to sensitive financial actions without simulating clicks on complex, security-sensitive UI elements.
For websites with WebMCP-enabled admin panels, agents can directly call tools to create blog posts, upload media, or update page content using structured schemas. This bypasses the need to automate form filling and button clicks in dynamic CMS interfaces.
On travel sites, agents can use WebMCP tools to search flights, select seats, and book reservations with built-in user confirmation flows. This ensures reliable booking automation as tools adapt to real-time availability changes without DOM dependency.
Within helpdesk software, agents can invoke WebMCP tools to create tickets, assign priorities, or add notes based on customer queries. This allows precise interaction with ticket systems that update dynamically as agents navigate between support queues.
Offer a subscription-based platform where businesses integrate WebMCP into their web apps, enabling AI agents to perform tasks like data entry, customer support, or transaction processing. Revenue comes from tiered plans based on tool usage volume and support levels.
Provide consulting and development services to large companies for embedding WebMCP tools into their internal web applications (e.g., HR systems, inventory management). Revenue is generated through project-based contracts and ongoing maintenance fees.
Create a marketplace for browser extensions that leverage WebMCP tools to enhance user productivity on supported websites. Revenue is earned via paid extensions, freemium models, or commissions on sales, targeting users who automate repetitive web tasks.
💬 Integration Tip
Start by adding WebMCP to key user actions like form submissions or data queries, and use provideContext() during SPA state changes to keep tools updated without requiring page reloads.
Scored Apr 19, 2026
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
通过 macOS Accessibility API 控制小红书(rednote)App。支持私信、评论回复、视频评论读取、搜索、点赞、收藏、作者数据等。需要 Mac + rednote App 可见 + Terminal 辅助功能权限。
AI-first security intelligence with LLM-powered intent analysis. 743+ findings from 361+ skill audits, 25 pattern rules, 22 attack classes.
OpenAMC 本地 MCP 命令调用技能。通过标准化 CLI 接口,允许 AI Agent 主动向本地 MCP Server 发送查询指令以获取全球金融数据。覆盖 A股/港股(AKShare)、美股(yfinance)、宏观经济(FRED/IMF/EconDB)、美国国会(Congress)及衍生品、外汇、大宗...
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions, troubleshooting AI_APICallError, Workers startup issues, Output API errors, Gemini caching issues, Anthropic tool errors, MCP tools, or stream resumption failures.