# Knocklog (remote · api.knocklog.ai)

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

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.knocklog.ai`: 74/100 (this document), [markdown](https://verifymcp.io/servers/leonlesenechal-knocklog/mcp-directory.md), [page](https://verifymcp.io/servers/leonlesenechal-knocklog/mcp-directory)

## Channel facts

- Endpoint: `https://api.knocklog.ai/mcp/directory`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 500 tokens (~125/item across 4 items; 3 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Knocklog MCP server?

Knocklog is a hosted endpoint at https://api.knocklog.ai/mcp/directory, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http leonlesenechal-knocklog 'https://api.knocklog.ai/mcp/directory'
```

### Cursor

```json
{
  "mcpServers": {
    "leonlesenechal-knocklog": {
      "url": "https://api.knocklog.ai/mcp/directory"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.leonlesenechal-knocklog]
url = "https://api.knocklog.ai/mcp/directory"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "leonlesenechal-knocklog": {
      "type": "remote",
      "url": "https://api.knocklog.ai/mcp/directory",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add leonlesenechal-knocklog --url 'https://api.knocklog.ai/mcp/directory' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  leonlesenechal-knocklog:
    url: "https://api.knocklog.ai/mcp/directory"
```

### Netclaw

```json
{
  "McpServers": {
    "leonlesenechal-knocklog": {
      "Transport": "http",
      "Url": "https://api.knocklog.ai/mcp/directory"
    }
  }
}
```

### Vellum

```bash
assistant mcp add leonlesenechal-knocklog -t streamable-http -u 'https://api.knocklog.ai/mcp/directory'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 69, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-09 (score 68)

First indexed and scored.

## MCP tools (3)

### `scan_site` (~97 tokens)

Scan a site for AI-agent readiness

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.

Input parameters:

- `domain` (string, required): Domain or URL, e.g. example.com

### `classify_request` (~161 tokens)

Identify and verify one HTTP 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.

Input parameters:

- `headers` (object): Request headers
- `ip` (string): Client IP as seen by the server
- `method` (string): HTTP method of the request (default GET)
- `url` (string): Full request URL
- `user_agent` (string): The User-Agent header of the request, exactly as received

### `list_known_agents` (~77 tokens)

List known AI 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.

Input parameters:

- `agent_class` (string): Only agents of this kind, e.g. training_crawler, ai_search_crawler or user_action_agent

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/leonlesenechal-knocklog/mcp-directory#diagnostics

## Score history

- 2026-11-21: 74
- 2026-11-20: 73
- 2026-11-19: 73
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 71
- 2026-11-15: 71
- 2026-11-14: 71
- 2026-11-13: 70
- 2026-11-12: 70
- 2026-11-11: 69
- 2026-11-10: 69
- 2026-11-09: 68

## Common questions

### What is the Knocklog MCP server?

Knocklog is an MCP server listed in the public MCP registry as io.github.leonlesenechal/knocklog. See how a website treats AI agents, and check whether a ChatGPT, Claude or Perplexity visit is real. This page covers its hosted endpoint (https://api.knocklog.ai/mcp/directory).

### Is the Knocklog MCP server safe to use?

Knocklog scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Knocklog MCP server expose?

Knocklog exposes 3 tools: scan_site, classify_request, list_known_agents. Their descriptions and schemas cost roughly 335 tokens of context every time the server is loaded.

### Does the Knocklog MCP server require authentication?

No. We connected to Knocklog without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Knocklog MCP server still maintained?

Knocklog is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Knocklog MCP server?

VerifyMCP ran 13 checks on Knocklog, covering TLS certificate, Authorization, HSTS header, DNSSEC and 9 more. One item could not be completed, a gap on our side rather than a finding about Knocklog: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.knocklog.ai/mcp/directory
- Repository: https://github.com/knocklog/api
- Website: https://knocklog.ai/
- Changelog RSS feed: https://verifymcp.io/servers/leonlesenechal-knocklog/mcp-directory.xml
- Changelog JSON feed: https://verifymcp.io/servers/leonlesenechal-knocklog/mcp-directory/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/leonlesenechal-knocklog/mcp-directory.json
- HTML version of this page: https://verifymcp.io/servers/leonlesenechal-knocklog/mcp-directory
