Metrickle
Start free

Your analytics, inside Claude and any MCP client

Metrickle is a remote MCP server. Connect Claude or any MCP client with a personal token, and it can read the same analytics you see in the dashboard, then draft goals, funnels, tasks and surveys for a person to review.

Connect your assistant What it can and can't do 
# Token from Connect AI in the dashboard
claude mcp add --transport http metrickle \
  https://app.metrickle.com/mcp \
  --header "Authorization: Bearer mk_sk_…"

# Then ask
> Why did trial signups on acme.com drop
  last week?

  get_app_summary · get_breakdown · run_funnel
  Signups fell 18%. Almost all of the drop is
  utm_source=newsletter, whose sessions now
  land on /pricing/old and u-turn.

Connected in two minutes

The server lives at https://app.metrickle.com/mcp and speaks Streamable HTTP, so any client that supports remote MCP servers can use it.

  1. Create a token

    In the dashboard, open Connect AI, name the token, pick “Read only” or “Read and draft”, and optionally set an expiry of up to a year.

  2. Add the server

    Run claude mcp add as shown above, or add the URL and an Authorization: Bearer header in your client's settings.

  3. Ask a question

    Start with “list my apps”, then ask about any app, page, campaign or funnel in plain words.

Everything the dashboard can answer

Every read tool takes a period or an ISO date range, plus the same filters as the dashboard: page, event, campaign, country, device, app version, accessibility setting and survey answer.

Portfolio and apps

list_apps, get_portfolio, get_app_summary and get_timeseries: every app with period-over-period changes.

Breakdowns

get_breakdown by page, event, referrer, country, device, app version, accessibility setting, or utm_campaign and utm_source for marketing campaigns.

Goals, funnels and tasks

list_goals, list_funnels, run_funnel, list_tasks and run_task, including funnels that haven't been saved yet.

Friction and journeys

get_friction, get_journeys, get_retention and get_recent_events.

Releases

list_releases: what shipped in the period, so the assistant can tie a change in a metric to a deploy.

Surveys and feedback

list_survey_campaigns, get_survey_results and list_feedback.

Install and check

get_install_guide gives the snippet for your stack with your write key filled in, and verify_install confirms events are arriving or says what to fix.

Same tokens, REST too

The same token works as a bearer token on the /api/v1 read endpoints, for scripts and notebooks.

From question to a saved funnel

Tokens with “Read and draft” access also get create_app, create_goal, create_funnel, create_task, create_survey_draft and update_survey_draft. Read-only tokens don't see these tools at all.

Three built-in prompts do the legwork for the most common requests.

  • setup-metrickle: in a coding assistant like Claude Code, works out your stack, picks or creates the app, adds the SDK and a couple of key events to your code, then checks events arrive and suggests your first goals.
  • build-funnel: finds the events and pages that really make up a journey, runs the funnel, names the biggest leak, checks its friction and splits it by device, accessibility setting and source. It saves nothing until you agree.
  • plan-survey: checks the data first, proposes one to three plain-language questions with a trigger, sample and frequency, and saves the survey as a draft once you agree.
Drafted by build-funnelOrbit iOS · last 30 days · 14-day window
Entered4,380
Upgraded2676.1%
Median time2d 4h
onboarding_done100%
project_created58%
Paywall21%
upgrade6.1%

Biggest leak: project_created → Paywall (−64%)

Every step matched real data before it was proposed. The assistant ran the funnel, then offered to save it.

An assistant with exactly your access, and less

A token acts as the person who created it, with their role in each workspace. Every request goes through the same access checks and validation as the dashboard, and the limits are enforced by the server, not only by the MCP layer.

What each kind of token can do
ActionRead onlyRead and draft
Read analytics, funnels, tasks, friction, journeys, retention, surveys and feedbackYesYes
Create goals, funnels and tasksNoYes
Create and edit surveysNoYes, as drafts only
Activate a surveyNoNo
Delete or erase data, rotate keys, change settings, manage tokensNoNo
  • Only a SHA-256 hash is stored. The token is shown once, when you create it.
  • Revoke any time under Connect AI, or give a token an expiry when you create it.
  • Surveys stay drafts until a person activates them in the dashboard.
  • End-user text is labelled: the server tells assistants that feedback, survey answers and event properties are written by end users, to be treated as data and never as instructions.

Common questions

Which AI assistants work with Metrickle?

Any MCP client that supports remote servers over Streamable HTTP with a bearer token header, including Claude Code. Add https://app.metrickle.com/mcp with the header Authorization: Bearer followed by your token.

Can the assistant delete data or change settings?

No. No token can delete, erase, rotate keys, change settings or manage tokens. The most a token can do is create goals, funnels and tasks, and create or edit survey drafts.

Which apps can the assistant see?

The same apps you can see. A token acts as you, with your role in each workspace, so it can read every workspace you belong to. Create it with “Read only” access if you don't want it to create anything.

How are tokens stored?

Only a SHA-256 hash of each token is stored. The token itself is shown once, when you create it. You can revoke a token at any time, or set it to expire after up to 365 days.

See where your apps break, and who they break for

Free to start. One script tag on the web, one SDK on mobile, and no cookie banner in cookieless mode.

Start tracking for free