What is the Browsegrab MCP server?
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
How to install Browsegrab
Copy-paste configuration for popular MCP clients.
transport: stdio
Config generated by PluginBench — verify against the source before use.Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"browsegrab": {
"command": "uvx",
"args": [
"browsegrab"
]
}
}
}Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"browsegrab": {
"command": "uvx",
"args": [
"browsegrab"
]
}
}
}Windsurf
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"browsegrab": {
"command": "uvx",
"args": [
"browsegrab"
]
}
}
}VS Code
.vscode/mcp.json
{
"servers": {
"browsegrab": {
"type": "stdio",
"command": "uvx",
"args": [
"browsegrab"
]
}
}
}Claude Code
claude mcp add browsegrab -- uvx browsegrabRelated MCP servers
Docpick
Maintained
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
1
View repository →Apache-2.0
Diffgrab
Maintained
Web page change tracking with structured diffs. markgrab + snapgrab integration.
0
View repository →MIT
Embgrep
Maintained
Local semantic search — embedding-powered grep for files, zero external services.
0
View repository →MIT
FeedKit
Maintained
RSS/Atom feed collection with 417 curated feeds. Python MCP server.
0
View repository →MIT
MarkGrab
Maintained
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
0
View repository →MIT
Snapgrab
Maintained
URL to screenshot with metadata. Python MCP server. Claude Vision optimized.
0
View repository →MIT