mcpField
P
Plausible MCP by usefulapi

Plausible MCP by usefulapi

Remote
usefulapi.ioData & Analytics0Updated today

About Plausible MCP by usefulapi

A hosted MCP server for querying Plausible Analytics, for users who want site metrics in an MCP client. It provides statistics, realtime visitor counts, property breakdowns and goals without local installation.

Key features

  1. 01Site statistics and aggregates
  2. 02Time-series queries
  3. 03Property breakdowns
  4. 04Realtime visitor counts
  5. 05Site and goal lists

Use cases

  1. 01Track site metrics over selected periods
  2. 02Check current realtime visitor counts
  3. 03Compare metrics by property
  4. 04Review configured goals

MCP support

Exposes read tools for Plausible site statistics, aggregates, timeseries, breakdowns, realtime visitors and goals to MCP clients. It is hosted remotely and uses OAuth sign-in with the user's Plausible API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://plausible-analytics.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

8
ParameterTypeRequiredDescription
filtersarrayNoOptional filters. Each is an array like ["is","visit:country_name",["Estonia"]] or ["contains","event:page",["/blog"]] with logical wrappers ["and",[...]] / ["or",[...]] / ["not",[...]]. Operators: is, is_not, contains, contains_not, matches, matches_not, has_done, has_not_done.
includeobjectNoOptional include flags: { imports?, time_labels?, total_rows? }.
include.importsbooleanNoInclude imported (pre-Plausible) stats.
include.total_rowsbooleanNoInclude the total number of rows in meta.
include.time_labelsbooleanNoInclude a full list of time labels for the range.
metricsarrayYesMetrics to compute. Any of: visitors, visits, pageviews, views_per_visit, bounce_rate, visit_duration, events, scroll_depth, percentage, conversion_rate, group_conversion_rate, average_revenue, total_revenue, time_on_page.
site_idstringYesThe site's domain as registered in Plausible, e.g. "example.com".
order_byarrayNoOptional ordering: an array of [metric_or_dimension, "asc"|"desc"] pairs, e.g. [["visitors","desc"]].
date_rangeanyYesDate range: a shortcut string ("day", "7d", "28d", "30d", "91d", "month", "6mo", "12mo", "year", "all", "24h") OR a 2-element ISO8601 array like ["2024-01-01","2024-07-01"] (dates or datetimes with tz).
dimensionsarrayNoGroup-by dimensions. Event dims (event:goal, event:page, event:hostname), visit dims (visit:source, visit:referrer, visit:utm_medium/source/campaign, visit:device, visit:browser, visit:os, visit:country/region/city[_name], visit:entry_page, visit:exit_page), time dims (time, time:hour, time:day, time:week, time:month), or custom props (event:props:<name>). Omit for totals.
paginationobjectNoOptional pagination: { limit?, offset? }.
pagination.limitintegerNoRows per page (default 10000).
pagination.offsetintegerNoRow offset (default 0).

Details

From the project README

Plausible MCP by usefulapi

Use your Plausible account from Claude, Cursor, or any MCP client — query site stats, realtime visitors, breakdowns and goals. Hosted, no local install: connect with your own credentials.

Live endpoint: https://plausible-analytics.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://plausible-analytics.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http plausible-analytics https://plausible-analytics.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
{
  "mcpServers": {
    "plausible-analytics": {
      "url": "https://plausible-analytics.usefulapi.io/mcp"
    }
  }
}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Plausible credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/plausible-analytics/

On first connect you'll provide your Plausible API key (Account Settings → API keys). It is validated, stored per-user, and scoped to you — no keys in config files.

Tools

ToolTypeWhat it does
plausible_query_statsreadQuery stats
plausible_aggregatereadAggregate totals
plausible_timeseriesreadTimeseries
plausible_breakdownreadBreakdown by property
plausible_realtime_visitorsreadRealtime visitors
plausible_list_sitesreadList sites
plausible_get_sitereadGet site
plausible_list_goalsreadList goals
plausible_analytics_usage_statusmetaUsage status (free-tier meter)
plausible_analytics_request_featuremetaRequest a missing feature
plausible_analytics_upgrademetaUpgrade to Pro (unlimited*)
plausible_analytics_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with plausible_analytics_upgrade (it returns a Stripe Checkout link). Cancel any time with plausible_analytics_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running plausible_analytics_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT — see LICENSE. Documentation only; the server is hosted.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.