Algonius Browser MCP connects an assistant to browser actions through a Chrome extension and a native messaging host.
Algonius Browser MCP connects an assistant to browser actions through a Chrome extension and a native messaging host.
Algonius uses a Chrome extension for browser interactions and a Go native messaging host to connect external MCP clients. Its documented tools cover navigation, tab management, DOM element discovery, clicks and value entry. The model proposes operations while the extension and host carry them out in the browser.
Building the TypeScript extension alone is not the complete setup. Follow the repository instructions for loading the extension and registering the native host. Confirm the host path and Chrome registration before diagnosing a missing MCP tool as a model problem.
Open a test page, inspect a known element, set an input value and verify the visible result. Then try a tab operation and an element that is absent. Review whether errors identify the failed action clearly. A discovered element can change after navigation, so obtain fresh page information before applying the next action.
Use the integration with the browser profile and pages intended for the task. An extension can interact with the pages allowed by its permissions, which deserves a separate review from the model’s prompt. The project is Apache-2.0 licensed and maintained in the linked repository. This profile does not claim that the community bridge supplies every feature of another browser automation server.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| navigate_to | Navigate a browser tab. |
| manage_tabs | Manage browser tabs. |
| get_dom_extra_elements | Inspect relevant DOM elements. |
| click_element | Click a discovered page element. |
| set_value | Set a form field value. |
Chrome, the built extension and the registered native messaging host.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Enables AI-powered applications to monitor and interact with browser data via a Chrome extension and MCP.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript