# Knocklog

> See how a website treats AI agents, and check whether a ChatGPT, Claude or Perplexity visit is real.

- name: io.github.leonlesenechal/knocklog
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 92/100
- quality: 82/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.leonlesenechal%2Fknocklog
- tools: https://api.protogrid.dev/v1/servers/io.github.leonlesenechal%2Fknocklog/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "knocklog": {
      "type": "http",
      "url": "https://api.knocklog.ai/mcp/directory"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 98
- freshness: 100
- provenance: 75
- drivers: +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.

## Quality 82/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 88 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: scan_site (idempotentHint); classify_request (idempotentHint); list_known_agents (idempotentHint)
- pass `tools.token_cost`: about 576 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`, `stability.new_links`: tool history recorded for 4 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 576 tokens to load them all
- tool set hash: 3c61f54817d5a9dbd173245fae18c9bd
- tools last changed: 2026-11-10T01:12:29.811Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.leonlesenechal/knocklog.svg)](https://protogrid.dev/servers/io.github.leonlesenechal/knocklog)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-10 `list_known_agents` changed (inputSchema)
- 2026-11-10 `classify_request` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.leonlesenechal%2Fknocklog/changes

## Remotes

- https://api.knocklog.ai/mcp/directory (streamable-http, auth none, reachable true, uptime30d 0.9444444)

## Packages

_none_

## Tools (3)

- `classify_request`: 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_agents`: 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_site`: 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.