Knocklog is an MCP server published by io.github.leonlesenechal, hosted at api.knocklog.ai. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 3 tools, including scan_site, classify_request, list_known_agents.
See how a website treats AI agents, and check whether a ChatGPT, Claude or Perplexity visit is real.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| domain * | string | Domain or URL, e.g. example.com |
{
"name": "scan_site",
"title": "Scan a site for AI-agent readiness",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"description": "Domain or URL, e.g. example.com"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Scan a site for AI-agent readiness",
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| ip | string | Client IP as seen by the server |
| url | string | Full request URL |
| method | string | HTTP method of the request (default GET) |
| headers | object | Request headers |
| user_agent | string | The User-Agent header of the request, exactly as received |
{
"name": "classify_request",
"title": "Identify and verify one HTTP request",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"ip": {
"type": "string",
"description": "Client IP as seen by the server"
},
"url": {
"type": "string",
"description": "Full request URL"
},
"method": {
"type": "string",
"description": "HTTP method of the request (default GET)"
},
"headers": {
"type": "object",
"description": "Request headers",
"additionalProperties": {
"type": "string"
}
},
"user_agent": {
"type": "string",
"description": "The User-Agent header of the request, exactly as received"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Identify and verify one HTTP request",
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| agent_class | string | Only agents of this kind, e.g. training_crawler, ai_search_crawler or user_action_agent |
{
"name": "list_known_agents",
"title": "List known AI agents",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"agent_class": {
"enum": [
"training_crawler",
"ai_search_crawler",
"user_action_agent",
"agentic_browser",
"coding_agent",
"search_engine",
"preview_fetcher",
"ads_checker",
"automation_client",
"scraper"
],
"type": "string",
"description": "Only agents of this kind, e.g. training_crawler, ai_search_crawler or user_action_agent"
}
},
"additionalProperties": false
},
"annotations": {
"title": "List known AI agents",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Knocklog: analytics for AI agents. Use scan_site on a website's domain to see how it treats AI agents (robots.txt rules for each agent, content readable without JavaScript, llms.txt, markdown) and what to fix. Use classify_request to identify one HTTP request (User-Agent, IP, URL, headers) and verify whether the agent is who it claims to be. Use list_known_agents for the directory of AI agents with operator, type, robots.txt token and how each one can be verified. To measure a site's real agent traffic over time, the site owner creates a free project at https://knocklog.ai.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.