Marketing
amivisible.dev
An MCP server that audits and improves AI crawler visibility by checking which bots can access URLs, extracting the markdown AI agents see, and generating robots.txt, llms.txt, and IndexNow fixes.
ENDPOINT 1
https://amivisible.dev/mcp
MCP server metadata
- Name
- amivisible
- Version
- 1.0.0
amivisible checks whether AI crawlers can see a site. No accounts, no state: every call is a fresh deterministic probe. Re-run check_site after deploying fixes to verify the change.
Known tools 3
check_siteCheck which AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Googlebot…) can actually see and read a URL.
Inferred read-onlyget_markdownSee a page through an agent's eyes: the markdown an AI actually extracts from it.
Inferred read-onlyget_fix_kitGenerate a fix kit for a site: corrected robots.txt (citation bots allowed, training blocks preserved, aliases completed, fake tokens dropped), an llms.txt draft (honestly labeled speculative), and IndexNow setup steps.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.amivisible]
url = "https://amivisible.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"amivisible": {
"type": "http",
"url": "https://amivisible.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: amivisible
Remote MCP URL: https://amivisible.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"amivisible": {
"url": "https://amivisible.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"amivisible": {
"type": "http",
"url": "https://amivisible.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "amivisible",
"transport": "streamable-http",
"url": "https://amivisible.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.