Zum Inhalt springen
TakoAPI
Zurück zu den Skills

outlit-mcp

von leo-paz

Marketing & Sales
437Downloadzahlen laut clawskills.sh
1Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

Use when querying Outlit customer data via MCP tools (outlit_*)

Beschreibung

Was dieser Skill macht

Connects to Outlit's MCP server and exposes 6 tools for querying customer intelligence data: customer and user profiles, revenue metrics, activity timelines, and raw SQL access against ClickHouse analytics tables. Monetary values are in cents, pagination is cursor-based, and SQL is read-only SELECT.

Querying Outlit data through MCP tools lets you combine customer lookups, timeline inspection, and custom SQL in a single conversational session without switching between dashboards.

Wann du ihn einsetzt

  • Finding paying customers with no product activity in the last 30 days
  • Breaking down monthly recurring revenue by billing status with SQL
  • Pulling a full activity timeline for a specific customer account
  • Identifying users stuck in early journey stages like SIGNED_UP or DISCOVERED
  • Running ad-hoc cohort queries against raw events and MRR snapshot tables

Beispiel-Workflow

EINGABE

User asks: Which paying customers haven't been active in 30 days, sorted by MRR?

AGENT
  1. 1

    Call outlit_list_customers with billingStatus PAYING, noActivityInLast 30d, orderBy mrr_cents, orderDirection desc

  2. 2

    Receive paginated list of at-risk customers with MRR in cents

  3. 3

    Convert mrr_cents to dollars by dividing by 100

  4. 4

    Check pagination.hasMore and fetch additional pages if needed

  5. 5

    Return ranked customer list with names, domains, and MRR

AUSGABE

Sorted list of paying customers inactive for 30+ days, each showing name, domain, and monthly revenue in dollars

Voraussetzungen

  • Outlit account at app.outlit.ai
  • Outlit API key generated from Settings > MCP Integration in the Outlit dashboard

Installation

clawhub install leo-paz/outlit-mcp

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links