An AI agent for analytics and reporting — turning any enriched or scraped dataset into a client-facing report or dashboard spec — backed by real analytics APIs.
Part of Agency Agents OS, an open ecosystem of specialized AI agents for real business work.
- Agency Agents OS — the central catalog this repo is part of.
- ai-seo-agent — one of the data sources this repo can turn into a report or dashboard.
- ai-ecommerce-agent — another data source this repo can report on.
- ai-competitor-intelligence-agent — shares this repo's cross-umbrella data-aggregation role.
- MuAPI MCP docs — connect this repo's
SKILL.mdfiles via MCP. - MuAPI Agent Skills — background on the
SKILL.mdpattern this repo uses. - MuAPI access keys — create the API key this agent needs.
This repo is the umbrella for turning raw numbers into something a client can actually read: a written report with takeaways, or a dashboard spec a BI tool can be built from. It's a cross-cutting umbrella — it doesn't collect its own data, it consumes datasets produced by other Agency Agents OS umbrellas (ai-sales-agent, ai-social-agent, ai-ecommerce-agent, ai-ads-agent, and others) and turns them into deliverables.
| Agent | Does | Status |
|---|---|---|
| Report Generation | Turns a raw dataset into a structured, client-facing written report with key takeaways | Coming Soon |
| Dashboard Builder | Turns a raw dataset into a structured dashboard spec (metrics, chart types, layout) | Coming Soon |
analytics.ga4_report— pull a structured analytics report for a given property/date range.analytics.aggregate_dataset— aggregate and summarize an arbitrary dataset (rows/columns from another umbrella's output) into report- or dashboard-ready metrics.
See each sub-agent's SKILL.md for the specific capabilities it uses.
- Create a Muapi account and API key at muapi.ai.
- Review the Muapi API quickstart and OpenAPI schema for the analytics endpoints.
- Load the
SKILL.mdfor the sub-agent you need into your agent runtime (hosted agent, MCP client, or custom LLM app), or follow it manually.
Every sub-agent's SKILL.md is model- and runtime-agnostic — it's plain Markdown, so it works with any LLM agent, not just Claude. Two integration paths:
As an MCP connection (the agent gets live Muapi tools):
Muapi runs an MCP server at https://api.muapi.ai/mcp that any MCP-compatible client can connect to — Cursor, Windsurf, Claude, or your own custom agent.
- Cursor / Windsurf / other clients with a header field: connect to
https://api.muapi.ai/mcpwith anAuthorization: Bearer YOUR_MUAPI_KEYheader. - claude.ai / Claude Cowork / other connector UIs with no header field: use the URL-embedded key form instead,
https://api.muapi.ai/mcp/YOUR_MUAPI_KEY, via Settings → Connectors → Add custom connector. - Claude Code / Claude Desktop:
claude mcp add muapi -e MUAPI_API_KEY=YOUR_MUAPI_KEY -- muapi mcp serve(uses the muapi CLI's stdio transport — Claude Code's HTTP MCP client doesn't reliably inject tools).
Full setup details for every client: muapi.ai/docs/mcp.
As agent instructions (any LLM follows the workflow directly):
Drop a sub-agent's SKILL.md into a Claude Code project's .claude/skills/ directory, paste it into a custom-GPT/Project's system instructions, hand it to an autonomous agent framework as a tool spec, or attach it directly in a chat conversation — then ask the agent to follow it.
Both sub-agents are read-only/draft-only: they read a dataset and produce a report or dashboard spec, never a live publish. Handing a dashboard spec to an actual BI tool, or a report to a client-facing channel, is a separate, explicitly approved step outside this repo.
Both sub-agents are Coming Soon. They depend on analytics and reporting capabilities (analytics.ga4_report, analytics.aggregate_dataset) that aren't yet live on Muapi. Until then, treat the SKILL.md files as blueprints, not working integrations.