Data & analysis

Outlit MCP

Try it

Use when querying Outlit customer data via MCP tools (outlit_*). Triggers on customer analytics, revenue metrics, activity timelines, cohort analysis, churn...

What it does

Query customer intelligence data through 6 MCP tools covering customer and user profiles, revenue metrics, activity timelines, and raw SQL analytics access.

The skill document

Outlit MCP Server

Query customer intelligence data through 6 MCP tools covering customer and user profiles, revenue metrics, activity timelines, and raw SQL analytics access.

Quick Start

What you needTool
Browse/filter customersoutlit_list_customers
Browse/filter usersoutlit_list_users
Single customer deep diveoutlit_get_customer
Customer activity historyoutlit_get_timeline
Custom analytics / aggregationsoutlit_query (SQL)
Discover tables & columnsoutlit_schema

Before writing SQL: Always call outlit_schema first to discover available tables and columns.

Common Patterns

Find at-risk customers:

{
  "tool": "outlit_list_customers",
  "billingStatus": "PAYING",
  "noActivityInLast": "30d",
  "orderBy": "mrr_cents",
  "orderDirection": "desc"
}

Revenue breakdown (SQL):

{
  "tool": "outlit_query",
  "sql": "SELECT billing_status, count(*) as customers, sum(mrr_cents)/100 as mrr_dollars FROM customer_dimensions GROUP BY 1 ORDER BY 3 DESC"
}

MCP Setup

Get an API Key

Go to Settings > MCP Integration in the Outlit dashboard (app.outlit.ai).

Auto-Detection Setup

Detect the current environment and run the appropriate setup command:

  1. Check for Claude Code — If running inside Claude Code (check if claude CLI is available), run:

    claude mcp add outlit https://mcp.outlit.ai/mcp -- --header "Authorization: Bearer API_KEY"
    
  2. Check for Cursor — If .cursor/mcp.json exists in the project or home directory, add to that file:

    {
      "mcpServers": {
        "outlit": {
          "url": "https://mcp.outlit.ai/mcp",
          "headers": { "Authorization": "Bearer API_KEY" }
        }
      }
    }
    
  3. Check for Claude Desktop — If claude_desktop_config.json exists at ~/Library/Application Support/Claude/ (macOS) or %APPDATA%/Claude/ (Windows), add to that file:

    {
      "mcpServers": {
        "outlit": {
          "url": "https://mcp.outlit.ai/mcp",
          "headers": { "Authorization": "Bearer API_KEY" }
        }
      }
    }
    

Ask the user for their API key if not provided. Replace API_KEY with the actual key.

Verify Connection

Call outlit_schema to confirm the connection is working.


Tool Reference

outlit_list_customers

Filter and paginate customers.

Key ParamsValues
billingStatusNONE, TRIALING, PAYING, CHURNED
hasActivityInLast / noActivityInLast7d, 14d, 30d, 90d (mutually exclusive)
mrrAbove / mrrBelowcents (10000 = $100)
searchname or domain
orderBylast_activity_at, first_seen_at, name, mrr_cents
limit1-1000 (default: 20)
cursorpagination token

outlit_list_users

Filter and paginate users.

Key ParamsValues
journeyStageDISCOVERED, SIGNED_UP, ACTIVATED, ENGAGED, INACTIVE
customerIdfilter by customer
hasActivityInLast / noActivityInLastNd, Nh, or Nm (e.g., 7d, 24h) — mutually exclusive
searchemail or name
orderBylast_activity_at, first_seen_at, email
limit1-1000 (default: 20)
cursorpagination token

outlit_get_customer

Single customer deep dive. Accepts customer ID, domain, or name.

Key ParamsValues
customercustomer ID, domain, or name (required)
includeusers, revenue, recentTimeline, behaviorMetrics
timeframe7d, 14d, 30d, 90d (default: 30d)

Only request the include sections you need — omitting unused ones is faster.

outlit_get_timeline

Activity timeline for a customer.

Key ParamsValues
customercustomer ID or domain (required)
channelsSDK, EMAIL, SLACK, CALL, CRM, BILLING, SUPPORT, INTERNAL
eventTypesfilter by specific event types
timeframe7d, 14d, 30d, 90d, all (default: 30d)
startDate / endDateISO 8601 (mutually exclusive with timeframe)
limit1-1000 (default: 50)
cursorpagination token

outlit_query

Raw SQL against ClickHouse analytics tables. SELECT only. See SQL Reference for ClickHouse syntax and security model.

Key ParamsValues
sqlSQL SELECT query (required)
limit1-10000 (default: 1000)

Available tables: events, customer_dimensions, user_dimensions, mrr_snapshots.

outlit_schema

Discover tables and columns. Call with no params for all tables, or table: "events" for a specific table. Always call this before writing SQL.


Data Model

Billing status: NONE → TRIALING → PAYING → CHURNED

Journey stages: DISCOVERED → SIGNED_UP → ACTIVATED → ENGAGED → INACTIVE

Data formats:

  • Monetary values in cents (divide by 100 for dollars)
  • Timestamps in ISO 8601
  • IDs with string prefixes (cust_, contact_, evt_)

Pagination: All list endpoints use cursor-based pagination. Check pagination.hasMore before requesting more pages. Pass pagination.nextCursor as cursor for the next page.


Best Practices

  1. Call outlit_schema before writing SQL — discover columns, don't guess
  2. Use customer tools for single lookups — don't use SQL for individual customer queries
  3. Filter at the source — use tool params and WHERE clauses, not post-fetch filtering
  4. Only request needed includes — omit unused include options for faster responses
  5. Always add time filters to event SQLWHERE occurred_at >= now() - INTERVAL N DAY
  6. Convert cents to dollars — divide monetary values by 100 for display
  7. Use LIMIT in SQL — cap result sets to avoid large data transfers

Known Limitations

  1. SQL is read-only — no INSERT, UPDATE, DELETE
  2. Organization isolation — cannot query other organizations' data
  3. Timeline requires a customer — cannot query timeline across all customers
  4. MRR filtering is post-fetch — may be slower on large datasets in list_customers
  5. Event queries need time filters — queries without date ranges scan all data
  6. ClickHouse syntax — uses different functions than MySQL/PostgreSQL (see SQL Reference)

Tool Gotchas

ToolGotcha
outlit_list_customershasActivityInLast and noActivityInLast are mutually exclusive
outlit_list_customerssearch checks name and domain only
outlit_get_customerbehaviorMetrics depends on timeframe — extend it if empty
outlit_get_timelinetimeframe and startDate/endDate are mutually exclusive
outlit_queryUse ClickHouse date syntax: now() - INTERVAL 30 DAY, not DATE_SUB()
outlit_queryproperties column is JSON — use JSONExtractString(properties, 'key')

References

ReferenceWhen to Read
SQL ReferenceClickHouse syntax, security model, query patterns
WorkflowsMulti-step analysis: churn risk, revenue dashboards, account health

Related skills

Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.

by nssa.io1.0k installs47 stars

Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.

by Iván555 installs18 stars

Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.

by johnpatternai21 installs8 stars

Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.

by fly0pants4.3k installs296 stars

Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.

by Iván854 installs69 stars

More from leo-paz

Browse all skills

Ground customer intelligence work in real product, conversation, billing, support, CRM, and web data via Outlit's CLI, MCP, and Pi tools.

by leo-paz35 installs3 stars

Step-by-step decision tree for adding Outlit tracking to web, server, native, and desktop apps.

by leo-paz44 installs