$ loading_
Turn browsers into MCP servers by relaying tools and resources to agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "webmcp-polyfill" yet — see the docs or source repo.
Use webmcp-polyfill to connect to the current browser, expose page tools to the AI, automatically inspect console errors, network requests, and DOM state, then suggest fixes.
A diagnosis of page issues with actionable fixes.
Use webmcp-polyfill to read the current page resources, extract key information, and generate a concise summary for reporting.
A concise summary with key bullet points.
Use webmcp-polyfill to relay a custom prompt to the AI agent through the WebSocket-to-stdio bridge, and verify tools, resources, and prompts are all accessible.
A connectivity check result and list of available capabilities.
Expose website JavaScript functions as MCP tools for AI browser interaction.
Connect MCP clients to browser apps and use Web APIs as resources.
Automate real browser tasks tab by tab while keeping the current session.
Control Windows Chrome from WSL for low-overhead web automation and debugging.
Control a browser through MCP for web actions, form filling, and screenshots
Control Chrome via MCP for browsing, form filling, screenshots, and logs.