Search / io.github.leonlesenechal/knocklog
protogridR0· no sign-inSee how a website treats AI agents, and check whether a ChatGPT, Claude or Perplexity visit is real.
v1.0.1 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"knocklog": {
"type": "http",
"url": "https://api.knocklog.ai/mcp/directory"
}
}
}claude mcp add --transport http knocklog https://api.knocklog.ai/mcp/directory[mcp_servers.knocklog]
url = "https://api.knocklog.ai/mcp/directory"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"knocklog": {
"type": "remote",
"url": "https://api.knocklog.ai/mcp/directory",
"enabled": true
}
}
}{
"mcpServers": {
"knocklog": {
"type": "http",
"url": "https://api.knocklog.ai/mcp/directory"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=knocklog&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLmtub2NrbG9nLmFpL21jcC9kaXJlY3RvcnkifQ%3D%3D"
}{
"servers": {
"knocklog": {
"type": "http",
"url": "https://api.knocklog.ai/mcp/directory"
}
}
}{
"mcpServers": {
"knocklog": {
"httpUrl": "https://api.knocklog.ai/mcp/directory"
}
}
}extensions:
"knocklog":
enabled: true
name: "knocklog"
type: streamable_http
uri: "https://api.knocklog.ai/mcp/directory"
timeout: 300
protocol.modernprotocol.statelessprotocol.transportprotocol.list_ttlauth.prm, auth.as_metadata, auth.cimdauth.secret_in_urltools.descriptionstools.description_lengthtools.schemastools.annotationstools.directory_hintstools.token_costtools.api_dumptools.hidden_textstability.changes, stability.rug_pull, stability.new_linksdeps.known_vulns, deps.mcp_sdk_version, deps.resolvablelist_known_agentschangedinput schemaclassify_requestchangedinput schemaFull history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +website +reachable +uptime-94% +updated-4d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://api.knocklog.ai/mcp/directory streamable-http | none | yes | 94% | 346 ms | 2025-11-25 | 2026-11-14 |
classify_requestread-only | Identifies whether a request comes from an AI agent, which one, what kind (training, AI search, user-triggered, agentic browser…) and whether its identity is verified or spoofed, using what each operator publishes (IP lists, reverse DNS, Web Bot Auth signatures; see https://knocklog.ai/agents). Pass the client IP, the full request URL and all request headers for the most complete check. |
list_known_agentsread-only | Returns the directory of known AI agents and crawlers: operator, class, robots.txt token, whether they honour robots.txt, and how each can be verified. Optionally filter by agent_class. |
scan_siteread-only | Checks a public website from the outside: which AI agents its robots.txt allows or blocks (training crawlers, AI search crawlers, user-triggered assistants), whether its content is readable without JavaScript, and whether it offers llms.txt and markdown. Returns a 0–100 score, a grade and prioritised findings with recommendations. Takes a few seconds. |
Schemas: list_tools.
{
"name": "io.github.leonlesenechal/knocklog",
"icons": [
{
"src": "https://knocklog.ai/icon-512.png",
"sizes": [
"512x512"
],
"mimeType": "image/png"
}
],
"title": "Knocklog",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://api.knocklog.ai/mcp/directory",
"type": "streamable-http"
}
],
"version": "1.0.1",
"repository": {
"url": "https://github.com/knocklog/api",
"source": "github"
},
"websiteUrl": "https://knocklog.ai",
"description": "See how a website treats AI agents, and check whether a ChatGPT, Claude or Perplexity visit is real."
}