rybbit-mcp

rybbit-mcp is a skill for Claude Code, Codex from nks-hub/rybbit-mcp. It costs 150 tokens per session (11,095 once invoked), scanned B, original, MIT.

A connection between a coding assistant and Rybbit Analytics, a privacy-focused, open-source web analytics platform that can be self-hosted. It lets the assistant query analytics data without opening the analytics dashboard.

In plain words
What is it for?
Use it to examine visits, pages, sessions, users, funnels, goals, custom events, JavaScript errors, and Core Web Vitals such as loading speed and layout stability.
Why use it?
It removes the need to manually inspect reports when investigating traffic, user behaviour, conversions, errors, or website performance.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it to examine visits, pages, sessions, users, funnels, goals, custom events, JavaScript errors, and Core Web Vitals such as loading speed and layout stability.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nks-hub/rybbit-mcp/rybbit-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add nks-hub/rybbit-mcp --skill rybbit-mcp
Clone the repo
git clone --depth 1 https://github.com/nks-hub/rybbit-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rybbit-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/nks-hub/rybbit-mcp/rybbit-mcp/github.svg)](https://agentmods.dev/skills/nks-hub/rybbit-mcp/rybbit-mcp)
Your own site
<a href="https://agentmods.dev/skills/nks-hub/rybbit-mcp/rybbit-mcp"><img src="https://agentmods.dev/badge/skills/nks-hub/rybbit-mcp/rybbit-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rybbit-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/nks-hub/rybbit-mcp/rybbit-mcp"><img src="https://agentmods.dev/badge/skills/nks-hub/rybbit-mcp/rybbit-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,095 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00150 $0.11095
Opus 5 $0.00075 $0.05548
Sonnet 5 $0.00030 $0.02219
Haiku 4.5 $0.00015 $0.01110

Measured 10d ago against content hash e6edc3ce3a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

rybbit-mcp scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add to `~/.claude/settings.json` or project `.claude/settings.json`:
SKILL.md · 1,014 lines

How it starts

The opening of the file, as written. The whole thing — 1,014 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rybbit Analytics MCP Server

1. Purpose & Context

Rybbit is a privacy-first, open-source web analytics platform — a self-hosted alternative to Google Analytics. Data is stored in ClickHouse + PostgreSQL. Tracking is done via a JavaScript snippet, TypeScript SDK (@nks-hub/rybbit-ts), or Flutter SDK (rybbit_flutter_sdk).

This MCP server exposes 31 tools that let Claude query any Rybbit Analytics instance directly — no dashboard needed. Claude can retrieve traffic overviews, drill into sessions and users, analyze funnels and goals, investigate errors, audit Core Web Vitals performance, track custom events, and manage sites.

Package: @nks-hub/rybbit-mcp v0.5.2 Stack: TypeScript, @modelcontextprotocol/sdk v1.27+, Zod, Node.js 18+ Transport: StdioServerTransport (local, for Claude Code)

2. Configuration

Environment Variables

Variable Required Description
RYBBIT_URL Yes Base URL of the Rybbit instance (e.g., https://analytics.example.com)
RYBBIT_API_KEY Recommended API key for Bearer token authentication
RYBBIT_EMAIL Alternative Email for email/password auth (uses better-auth session cookies)
RYBBIT_PASSWORD Alternative Password for email/password auth

Claude Code MCP Config

Add to ~/.claude/settings.json or project .claude/settings.json:

{
  "mcpServers": {
    "rybbit": {
      "command": "npx",
      "args": ["-y", "@nks-hub/rybbit-mcp"],
      "env": {
        "RYBBIT_URL": "https://your-rybbit-instance.com",
        "RYBBIT_API_KEY": "your-api-key"
      }
    }
  }
}

Or from a local clone:

{
  "mcpServers": {
    "rybbit": {
      "command": "node",
      "args": ["/path/to/rybbit-mcp/build/index.js"],
      "env": {
        "RYBBIT_URL": "https://analytics.example.com",
        "RYBBIT_API_KEY": "your-api-key"
      }
    }
  }
}

3. Workflow: Getting Started

  1. Always start with rybbit_list_sites to discover available sites and their IDs.
  2. Use rybbit_get_overview with a site ID for a quick traffic summary.
  3. Drill into specific areas as needed: metrics, sessions, users, events, errors, performance.

Read the full file on GitHub · 1,014 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 1,014 lines · 150 tokens per session scan B e6edc3ce3a78

Subscribe to this mod's changes

rybbit-mcp is a skill published in the GitHub repository nks-hub/rybbit-mcp (4 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 11,095 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.