Data Collection
desvela.ai
Monitors and retrieves information that domains publish for AI agents, and provides webhook notifications on changes.
ENDPOINT 1
https://registry.desvela.dev/mcp
MCP server metadata
- Name
- ai.desvela/registry
- Version
- 0.1.0
Known tools 4
watchSubscribe to a domain: get a signed webhook (X-Desvela-Signature, HMAC-SHA256) when what it publishes for AI agents changes — ai-catalog.
Inferred read-onlycrawler_block_testWhat the domain's CDN really does, as opposed to what its robots.
Inferred read-onlysearchNatural-language search over what Desvela has indexed: agents, MCP servers, registries — the same index as POST /search.
Potential side effectsCONNECT 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.ai-desvela-registry]
url = "https://registry.desvela.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"ai-desvela-registry": {
"type": "http",
"url": "https://registry.desvela.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: ai-desvela-registry
Remote MCP URL: https://registry.desvela.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": {
"ai-desvela-registry": {
"url": "https://registry.desvela.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"ai-desvela-registry": {
"type": "http",
"url": "https://registry.desvela.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "ai-desvela-registry",
"transport": "streamable-http",
"url": "https://registry.desvela.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for desvela.dev was fetched 2026-08-23T16:41:33.776Z.
desvela.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.