Browser automation through MCP for AI clients and agents.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Shiplight.
Shiplight MCP server provides browser automation through the Model Context Protocol. Its stated purpose is to let an MCP-compatible client or agent use browser automation capabilities. The available project information does not describe which browser actions are supported, whether sessions are persistent, or whether the server operates locally or remotely.
For developers, the primary fit is an agent workflow that needs to interact with a browser rather than only process text or call a conventional API. The supplied description does not identify a narrower use case, such as testing, scraping, form completion, navigation, or authenticated browsing. Those details should be confirmed from the project documentation before implementation.
The available material identifies Shiplight as an MCP server, so its browser automation capability is intended to be exposed to an MCP client. No transport or connection method is documented in the supplied information. There is also no information about whether the server uses standard input and output, HTTP, or another transport.
The project details do not explain how browser instances are created, how pages are selected, how actions are represented, or how results and errors are returned. They also do not state whether an external browser installation, a separate service, or credentials are required. Treat these as open integration questions when evaluating Shiplight MCP server.
The supported capability is browser automation. The supplied material does not provide names, schemas, parameters, return formats, or examples for individual tools. As a result, an implementation plan should not assume support for a particular action, including clicking, typing, navigation, screenshots, page extraction, downloads, or file uploads.
Shiplight MCP server may be relevant when the required task involves browser interaction, but tool-level suitability cannot be assessed from the available description alone. Review the current project documentation for the actual tool list and behavior before writing client code or agent instructions.
The README is unavailable, and the provided source contains no technical setup information. Supported MCP clients, operating systems, browser engines, authentication methods, environment variables, licensing terms, and installation commands are therefore unspecified.
The same information gap applies to reliability and operational behavior. There is no stated guidance on timeouts, concurrency, permissions, headless operation, session isolation, network access, or handling of sensitive browser data. These considerations matter for production automation and should be validated independently.
Based on the available material, the only confirmed selection criterion is browser automation over MCP. Shiplight MCP server should be evaluated further if your workflow depends on a specific browser, tool schema, deployment model, or client application.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/shiplight-2)<a href="https://allmcps.com/mcp/shiplight-2"><img src="https://allmcps.com/api/badge/shiplight-2?style=directory" alt="Shiplight on AllMCPs" /></a>