Kaminari Click MCP Server
Enables querying traffic-quality statistics, managing reports, and downloading IP/UA risk databases via MCP.
README
Kaminari Click MCP Server
Official Model Context Protocol server for Kaminari Click — connect Claude, Cursor, ChatGPT, or any MCP-capable agent to your traffic-quality statistics.
- Statistics — slice traffic by time, sub IDs, geo, device; compare periods; filter by any dimension.
- Reports — list, save, and delete saved reports; create public share links.
- Databases — check access to and download slices of the IP risk-score, VPN IP, and bot User-Agent databases.
Quick start
- Generate an API token in the Kaminari Click account settings (API section).
- Add the server to your client.
Cursor / Claude Code / any stdio client
{
"mcpServers": {
"kaminari-click": {
"command": "npx",
"args": ["-y", "@kaminari-click/mcp"],
"env": {
"KAMINARI_CLICK_API_KEY": "<your-api-token>"
}
}
}
}
Claude Desktop
Download kaminari-click-mcp.mcpb from the latest release and double-click to install. Claude Desktop asks for your API token during setup.
ChatGPT / hosted agents (HTTP)
Point the connector at https://mcp.kaminari.click/mcp. The server implements OAuth 2.0 (authorization code + PKCE + dynamic client registration): during authorization you paste your API token once, and the client receives it as its access token. Self-hosting:
KAMINARI_CLICK_TRANSPORT=http KAMINARI_CLICK_HTTP_PORT=8080 npx -y @kaminari-click/mcp
In HTTP mode every request must carry Authorization: Bearer <api-token>; the KAMINARI_CLICK_API_KEY env var is rejected so one tenant's token can never leak to another.
Tools
| Tool | Purpose |
|---|---|
list_stat_fields |
Grouping dimensions and metrics available to the account |
query_stats |
Query statistics with grouping, filters, and period comparison |
search_filter_values |
Autocomplete values for a dimension filter |
list_reports / get_report |
Browse saved reports |
save_report / delete_report |
Manage saved reports |
share_report / get_shared_report |
Public share links for report slices |
check_database_access |
Verify an IP/UA database subscription |
download_database |
Fetch a bounded CSV slice of an IP/UA database |
Configuration
All variables are prefixed KAMINARI_CLICK_ — see .env.example. Key ones:
| Variable | Default | Notes |
|---|---|---|
KAMINARI_CLICK_API_KEY |
— | Required in stdio mode; forbidden in http mode |
KAMINARI_CLICK_API_URL |
https://kaminari.click |
API base URL |
KAMINARI_CLICK_TRANSPORT |
stdio |
stdio or http (also --transport= flag) |
KAMINARI_CLICK_HTTP_PORT |
8080 |
HTTP mode listen port |
KAMINARI_CLICK_RATE_LIMIT_RPM |
120 |
Per-token rate limit in HTTP mode |
Development
npm install
npm run lint && npm run typecheck # static gates
npm run test:cov # tests + coverage gate (100% lines)
npm run build # npm package -> dist/
npm run build:mcpb-bundle # Claude Desktop bundle -> dist-mcpb/
npx @anthropic-ai/mcpb pack . kaminari-click-mcp.mcpb # .mcpb archive
Architecture: clean layering (domain → application → infrastructure / presentation), all dependencies flow through a per-request ToolContext, expected errors travel as Result<T, E> (neverthrow). The HTTP transport is stateless — any replica can serve any request — and API tokens never appear in logs.
Security
- Bearer tokens are wrapped in a self-redacting value object and never logged.
- HTTP mode builds a fresh API gateway per request; there is no cross-tenant state.
- The OAuth authorization server stores nothing beyond a 5-minute one-time code window.
Report vulnerabilities to security@kaminari.click.
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.