
Chrome over CDP for AI agents. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -32% time
Publisher config for Public Browser. Paste it into the client. This is not a PlugMCP endpoint.
{
"mcpServers": {
"io.github.silbercue-public-browser": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}{
"mcpServers": {
"io.github.silbercue-public-browser": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}claude mcp add io.github.silbercue-public-browser -- npx -y [email protected]
{
"servers": {
"io.github.silbercue-public-browser": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}No tool list on this record yet.
Last checked 2026-10-16. Publisher: io.github.Silbercue.
The publisher's own command. Not a PlugMCP endpoint.
npx -y [email protected]
claude mcp add io.github.silbercue-public-browser -- npx -y [email protected]
Run in a terminal.
{
"mcpServers": {
"io.github.silbercue-public-browser": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
Launchπ₯ Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Token-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Prepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.
Design or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.
Audit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testi
Chrome over CDP for AI agents. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -32% time
README is not crawled yet. Open the repository
No tool list yet. Remote servers get one after the first health check.