mrrscope
Enables querying MRRscope analytics (visitors, revenue, MRR, traffic sources, AI crawlers, realtime) via 6 read-only tools for AI agents.
README
mrrscope
Query your MRRscope analytics from the terminal β visitors, revenue, MRR, traffic sources, AI crawlers, realtime. Built for AI agents and LLMs π€
The CLI is a wrapper around the public API /api/v1: every command maps to a documented REST route, and --json prints the raw response.
Quick start
npx mrrscope login # paste an account token (create it in Settings β API)
npx mrrscope sites list
npx mrrscope analytics overview --site my-saas.com --period 30d
Or install globally:
npm install -g mrrscope
Commands
mrrscope login [--token mrt_xxx] # token saved to ~/.config/mrrscope/config.json
mrrscope logout
mrrscope sites list
mrrscope analytics overview --site my-saas.com --period 7d
mrrscope analytics timeseries --site my-saas.com --from 2026-01-01 --to 2026-01-31
mrrscope analytics pages --site my-saas.com --limit 25
mrrscope analytics referrers --site my-saas.com
mrrscope analytics countries --site my-saas.com
mrrscope analytics devices --site my-saas.com
mrrscope analytics crawlers --site my-saas.com # AI bots, IP-verified
mrrscope analytics realtime --site my-saas.com
mrrscope tokens list
mrrscope tokens create --name "SEO agent"
mrrscope tokens revoke <id>
For AI agents
# Compact JSON β pipe into jq, save to a file, feed an agent
MRRSCOPE_TOKEN=mrt_xxx mrrscope --json analytics overview --site my-saas.com | jq '.visitors'
Give your agent (Claude Code, Cursorβ¦) an mrt_ token and it can answer
"how many visitors yesterday?", "which pages earn?", "who is online right now?"
by running the CLI itself.
MCP server
The package also ships an MCP (Model Context Protocol) server β your agent discovers 6 read-only analytics tools by itself:
# Claude Code
claude mcp add mrrscope --env MRRSCOPE_TOKEN=mrt_xxx -- npx -y mrrscope mcp
// Claude Desktop / Cursor
{
"mcpServers": {
"mrrscope": {
"command": "npx",
"args": ["-y", "mrrscope", "mcp"],
"env": { "MRRSCOPE_TOKEN": "mrt_xxx" }
}
}
}
Tools: mrrscope_list_sites, mrrscope_overview, mrrscope_timeseries,
mrrscope_breakdown, mrrscope_crawlers, mrrscope_realtime.
MCP guide: https://mrrscope.com/docs/mcp
Authentication
Two token levels:
mrt_account token β full account: every site, plus token management. Create it in Settings β API.wf_site key β read-only analytics, limited to the sites it covers.
Environment overrides: MRRSCOPE_TOKEN, MRRSCOPE_API_BASE.
Docs
- CLI guide: https://mrrscope.com/docs/cli
- API reference: https://mrrscope.com/docs/api-v1
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.