Mira runs on your own machine — the client starts it, so there is no endpoint to ping.
Crawl a website and get its colors, fonts, logos, images and a Tailwind theme.
Today is the operative word: we check Mira every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mira -- npx -y mira-brand-mcp
{
"mcpServers": {
"mira": {
"command": "npx",
"args": [
"-y",
"mira-brand-mcp"
]
}
}
}
[mcp_servers.mira]
command = "npx"
args = ["-y", "mira-brand-mcp"]
{
"mcpServers": {
"mira": {
"command": "npx",
"args": [
"-y",
"mira-brand-mcp"
]
}
}
}
{
"servers": {
"mira": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mira-brand-mcp"
]
}
}
}
Find broken links on a website: crawls its pages and reports 404s, errors and redirect chains
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Crawl a website for links, file download links, HTML tables as rows, and lists, with no AI
Crawl and analyse websites for SEO errors using Crawlee with SQLite storage
Web pages and whole sites to clean Markdown for RAG and AI agents. Crawls links and sitemaps.
Crawls any website and generates a standards-compliant /llms.txt file and JSON-LD schema bundle.
Website crawling, Google search and Wikipedia lookup as agent tools.
Audit a business website for observed crawl and indexing issues with source-linked fixes.
Answers built from our own checks of this server.