MCP server that integrates with FE development server for Cursor
MCP server that integrates with FE development server for Cursor. Exposed over MCP by the blowback mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
A Model Context Protocol (MCP) server that integrates FE development servers with AI tools like Claude Desktop and Cursor.
Everything the assistant can do here goes through one of these:
get-hmr-events — Retrieves recent HMR eventscheck-hmr-status — Checks the HMR statusstart-browser — Starts a browser instance and navigates to the development server. HMR monitoring starts automaticallycapture-screenshot — Captures a screenshot of the current page or a specific element. Returns screenshot ID and resource URIget-element-properties — Retrieves properties and state information of a specific elementget-element-styles — Retrieves style information of a specific elementget-element-dimensions — Retrieves dimension and position information of a specific elementmonitor-network — Monitors network requests in the browser for a specified durationget-element-html — Retrieves the HTML content of a specific element and its childrenget-console-logs — Retrieves console logs from the browser session with optional filteringexecute-browser-commands — Safely executes predefined browser commandshow-to-use — Provides instructions on how to use specific features of the serverYou will need one environment variable: PROJECT_ROOT. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
The server ships on npm as blowback-context, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Blowback's toolset — get-hmr-events, check-hmr-status, start-browser and 10 more — is a fair guide to whether it matches your workflow. It is maintained by esnark; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| get-hmr-events | Retrieves recent HMR events |
| check-hmr-status | Checks the HMR status |
| start-browser | Starts a browser instance and navigates to the development server. HMR monitoring starts automatically |
| capture-screenshot | Captures a screenshot of the current page or a specific element. Returns screenshot ID and resource URI |
| get-element-properties | Retrieves properties and state information of a specific element |
| get-element-styles | Retrieves style information of a specific element |
| get-element-dimensions | Retrieves dimension and position information of a specific element |
| monitor-network | Monitors network requests in the browser for a specified duration |
| get-element-html | Retrieves the HTML content of a specific element and its children |
| get-console-logs | Retrieves console logs from the browser session with optional filtering |
| execute-browser-commands | Safely executes predefined browser commands |
| how-to-use | Provides instructions on how to use specific features of the server |
| screenshots | A resource for querying all captured screenshots. You can query screenshot reference IDs captured by the capture-screenshot tool using various criteria. |
{
"mcpServers": {
"blowback": {
"command": "npx",
"args": ["-y", "blowback-context"],
"env": {
"PROJECT_ROOT": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| PROJECT_ROOT | Configuration value read at startup. | Optional |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
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.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.