GEO-bot
Free check whether a website is technically open to AI assistants (AI crawlers, llms.txt, JSON-LD).
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"geo-bot": {
"url": "https://feelswebman.com/projects/geo-bot/mcp.php"
}
}
}Remote endpoints
https://feelswebman.com/projects/geo-bot/mcp.phpstreamable-httpWhat it can do
Tool inventory
Tools (1)
🟢check_ai_readiness(domain, language)
Checks whether a website is technically open to AI assistants: robots.txt rules for 9 AI crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot, Google-Extended, CCBot), presence of llms.txt, and on the home page the title, meta description and JSON-LD (Organization/LocalBusiness). Free, read-only, takes a few seconds. It does NOT measure whether any AI assistant actually recommends the brand (that is what the paid GEO-bot check does) and it only looks at the home page, robots.txt and llms.txt.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain or URL of the website, e.g. \"example.com\"."
},
"language": {
"type": "string",
"enum": [
"en",
"de"
],
"description": "Language of the report. Default \"en\"."
}
},
"required": [
"domain"
]
}Community
Evidence