| What it does | Hosted MCP server connecting Google Analytics, Ads and Search Console to Claude and ChatGPT
| An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | IE
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: 50 credits to ask in Caybl, Google Analytics in Claude/ChatGPT with unlimited questions, no card required. Pro: $29/month with 500 credits/month, all data sources (Google Ads, Search Console, Bing, Microsoft Advertising, Tag Manager, YouTube, PageSpeed), and unlimited questions in Claude/ChatG
| Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
|
|---|
| Key features | - Google Analytics connector with standard reports, realtime reports, funnel reports, account/property lookup, custom dimensions and metrics
- Search Console queries, pages and index status tracking
- Bing Webmaster Tools with crawl health, backlinks and keyword research
- Microsoft Advertising campaigns, keywords and performance management
- Tag Manager container audits and version history
- YouTube channel analytics including revenue for monetized channels
- PageSpeed Insights and Core Web Vitals auditing
- One-click disconnect with immediate OAuth revocation
- Built-in assistant powered by Claude with one-click fixes for negative keywords and budgets
| - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
|
|---|
| What makes it different | - No setup required - sign in once with Google, no tokens or credentials to manage
- Ask questions in your own AI (Claude, ChatGPT) with unlimited questions on all plans
- Write access with dry-run preview and approval required before any changes apply
- Data fetched on demand from live APIs, never stored or warehoused
| - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 2 ▼ −3 (down) since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 27 | 9 |
| Referring domains (Majestic) | 29 | 4 |