mcpField
K
Knocklog

Knocklog

Remote
knocklog.aiData & Analytics0Updated 4d ago

About Knocklog

Knocklog is an analytics API for site owners tracking AI-agent visits, request identity, and referrals from AI assistants. Its endpoints cover agent verification, traffic reports, and project management.

Key features

  1. 01Identify and verify AI-agent requests
  2. 02Scan how a site treats agents
  3. 03Report AI-agent traffic
  4. 04Import access logs
  5. 05Configure webhooks and integrations

Use cases

  1. 01Check whether a crawler request is genuine
  2. 02Review pages read by AI agents
  3. 03Measure visitors and leads sent by AI assistants

MCP support

Knocklog offers MCP access through public directory, account-specific, and full-tool endpoints. MCP clients can use its agent and analytics capabilities.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.knocklog.ai/mcp/directory
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Knocklog API

The public description of the Knocklog API: analytics for AI agents. See which AI agents visit a website, whether each one is who it claims to be, what they read, and the visitors and leads AI assistants send.

Quick start

# Check how a site treats AI agents (no key)
curl "https://api.knocklog.ai/v1/scan?domain=example.com"

# Identify one request
curl -X POST "https://api.knocklog.ai/v1/classify" -H "Content-Type: application/json" \
  -d '{"user_agent": "Mozilla/5.0; compatible; GPTBot/1.4; +https://openai.com/gptbot", "ip": "20.171.206.10"}'

# Create a project: returns an ingest key, an admin key and install code
curl -X POST "https://api.knocklog.ai/v1/projects" -H "Content-Type: application/json" -d '{"domain": "example.com"}'

# Read the report
curl "https://api.knocklog.ai/v1/traffic?days=30" -H "Authorization: Bearer $KNOCKLOG_ADMIN_KEY"

The ingest key (kl_ing_…) only sends traffic and is safe in a collector on the site. The admin key (kl_adm_…) reads reports; keep it private. More in examples/.

Endpoints

EndpointWhat it doesKey
GET /v1/agentsList known AI agentsnone
POST /v1/classifyIdentify and verify one requestnone
GET /v1/scanCheck how a site treats AI agentsnone
POST /v1/scanCheck how a site treats AI agents (JSON body)none
GET /v1/plansList plansnone
POST /v1/projectsCreate a projectnone
POST /v1/eventsSend requests from a collectoringest (optional)
POST /v1/logsImport access logsingest
GET /v1/planPlan and usageingest or admin
GET /v1/trafficTraffic reportadmin
GET /v1/accountAccount overviewadmin
GET /v1/ready-filesReady-made robots.txt and llms.txt (Pro)admin
POST /v1/keys/ingestNew ingest keyadmin
POST /v1/project/summaryWeekly summary by emailadmin
POST /v1/integrationsWebhook, Slack and company emailsadmin
POST /v1/install/cloudflareInstall the collector on Cloudflareadmin
POST /v1/billing/checkoutCheckout link for a paid planadmin
POST /v1/billing/portalLink to manage the subscriptionadmin
GET /v1/badge/{project}.jsonBadge statusnone
GET /v1/badge/{project}.svgBadge imagenone

Webhooks: company.visited and lead.from_ai, signed with x-knocklog-signature (example).

For AI agents

The same features over the Model Context Protocol:

  • https://api.knocklog.ai/mcp/directory: public tools, no sign-in
  • https://api.knocklog.ai/mcp/account: one project, OAuth sign-in
  • https://api.knocklog.ai/mcp: every tool, keys as arguments

Listed in the official MCP Registry as io.github.leonlesenechal/knocklog.

Also from Knocklog

Support

Questions or a missing endpoint: open an issue or write to [email protected]. Using the API is subject to the terms. The files in this repository are under the MIT license.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.