flowsery

Name: flowsery
Author: tarasshyn

Flowsery is AI session replay that finds bugs on autopilot, with a full web analytics layer underneath - and this MCP server puts both in front of your agent.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

List Websites: List websites accessible by the current API token. Workspace tokens return every website in the workspace; website keys return only their website. Call this first when using a workspace
Get Metadata: Get website configuration — domain, timezone, currency, KPI goal, and color scheme. With a workspace token, pass websiteId or domain; without one, this returns the website list.
Get Overview: Get aggregated site metrics: visitors, sessions, bounce rate, average session duration, revenue, revenue per visitor, and conversion rate. Supports date range and all filters. Omit dates

What data it sees

Do you need an account

No: the server works without sign-in

Flowsery is AI session replay that finds bugs on autopilot, with a full web analytics layer underneath - and this MCP server puts both in front of your agent.

Real-time visitors, site overview, time series, and breakdowns by page, referrer, country, device, UTM, channel, and more
Revenue attribution: payments from Stripe, Paddle, Polar, and Shopify tied back to the session that converted
Funnels, goals, custom events, and full visitor profiles with activity timelines
Issues found by the AI session review, with severity and affected sessions, queryable from Claude Code, Cursor, or ChatGPT

How to connect

How to connect flowsery to Claude

The server address to paste into Claude settings:

https://flowsery--tarasshyn.run.tools

Open Claude (claude.ai or the desktop app).
Go to Settings → Connectors.
Click Add custom connector.
Paste the server address copied below into Remote MCP server URL and click Add.
In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect flowsery to ChatGPT

The server address to paste into ChatGPT settings:

https://flowsery--tarasshyn.run.tools

Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
Open Settings → Connectors and click Create.
Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect flowsery to Cursor

The server address to paste into Cursor settings:

https://flowsery--tarasshyn.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (27)

Raw names from tools/list. Only developers need these.

list_websites	List websites accessible by the current API token. Workspace tokens return every website in the workspace; website keys return only their website. Call this first when using a workspace token.
get_metadata	Get website configuration — domain, timezone, currency, KPI goal, and color scheme. With a workspace token, pass websiteId or domain; without one, this returns the website list.
get_overview	Get aggregated site metrics: visitors, sessions, bounce rate, average session duration, revenue, revenue per visitor, and conversion rate. Supports date range and all filters. Omit dates for all-time data.
get_timeseries	Get time series analytics data grouped by hour, day, week, or month. Returns timestamped data points with totals. Use for trend analysis and charting.
get_realtime	Get the number of currently active visitors on the site (active within the last 5 minutes).
get_realtime_map	Get currently active visitors with geographic location data for map visualization.
get_pages	Get top pages ranked by visitor count. Shows which pages get the most traffic.
get_referrers	Get traffic sources — which websites and domains are sending visitors.
get_countries	Get visitor breakdown by country.
get_regions	Get visitor breakdown by region/state.
get_cities	Get visitor breakdown by city.
get_devices	Get device type breakdown — desktop vs mobile vs tablet split.
get_browsers	Get browser distribution — Chrome, Safari, Firefox, Edge, etc.
get_operating_systems	Get operating system distribution — Mac OS, Windows, iOS, Android, Linux, etc.
get_campaigns	Get UTM campaign performance — which campaigns drive the most traffic.
get_hostnames	Get traffic breakdown by hostname/domain.
get_channels	Get marketing channel breakdown — Organic Search, Paid Search, Social, Email, Direct, Referral, Affiliate, etc. GA4-aligned classification.
get_goals	Get goal/custom event completion stats within a date range.
get_breakdown	Generic breakdown by any dimension. Use this for dimensions that don't have a dedicated endpoint (e.g. entry_page, browser_version, os_version, utm_source, utm_medium, utm_term, utm_content, ref, source, all_params).
get_visitor	Get full visitor profile — identity (geo, device, browser, OS), traffic source, activity (visits, pages, goals), revenue (total, customer flag, time to first conversion), identified profile (userId, name, email), and a merged activity timeline. The visitor ID comes from the _fs_vid browser cookie.
list_issues	List issues the AI found while analyzing session recordings — bugs, broken flows, and UX problems, deduplicated across sessions and ranked by severity. Each issue includes how many sessions hit it, first/last seen times, and steps to replicate. Also returns open/in-progress/resolved counts.
get_issue	Get full detail for one AI-detected issue: every occurrence the AI flagged with timestamps, the sessions behind it, steps to replicate, comments, and any linked external ticket (Linear/Jira).
update_issue_status	Update an issue's status: open, in_progress, resolved, or suspended. Suspended issues disappear from the default list. Reversible — set any status back at any time.
track_goal	Track a custom goal/event for a visitor. The visitor must have at least one recorded pageview. Goal names must be lowercase with only letters, numbers, underscores, and hyphens (max 64 chars).
delete_goals	Delete custom goal events by filter. At least one filter is required. WARNING: without a date range, matching records are deleted across the entire history.
track_payment	Record a payment for revenue attribution. If you use Stripe, LemonSqueezy, or Polar, payments are tracked automatically — only use this for other providers.
delete_payments	Delete payment records by filter. At least one filter is required. WARNING: without a date range, matching records are deleted across the entire history.