Connectors · Observability & analytics

Plausible Analytics MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Plausible Analytics and the rest of your systems. It gives your agent 22 Plausible Analytics actions (12 reads, 6 writes and 4 that wait for a confirmation) and holds the Plausible Analytics credential itself, so the agent never does. It paces Plausible Analytics's limits and records every call.

Connect Plausible Analytics free See pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp

22actionsin one signed file
12readlook, never change
6writecreate and update
4wait for a yesdestructive, confirmed first

Set up

Connect Plausible Analytics in three steps.

01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp
02
Connect Plausible Analytics.
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.
- api_keyPlausible API key
- hostWhere your Plausible Analytics lives: your host
```
account { op: "connections.requirements", service: "plausible" }
# free: exactly what to paste, and what is found for you
```

Make the first call. Check before a write.

Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

do    { action: "plausible.sites.list" }# list sites list · read · 1 upstream callcheck { action: "plausible.sites.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Plausible Analytics at a glance

Sign-in: Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide: api_key
Setup fields: host
Limits we pace to: 600 calls an hour, per connection
API covered: Plausible Analytics (Stats API v2 and v1, Sites API) API stats v2 / sites v1plausible.io
Built from: Plausible Analytics's documentation, read 23 October 2026plausible.io plausible.io plausible.io
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 12 of 12 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 1, so ask can line Plausible Analytics up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Plausible Analytics.

22 actions in 1 area. Every one carries its effect, so a key can allow the reads and hold the rest.

12readlook, never change
6writecreate and update
4destructivewait for a confirmation

Web
22
12 read · 6 write · 4 destructive
List sites list · Create sites create · Get sites get · Update sites update

Top actions

The Plausible Analytics API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 5 of Plausible Analytics's 5 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`plausible.sites.list`List sites list	Lists the sites the API key can access.	read	`content.site.list`16 connectors
`plausible.sites.create`Create sites create	Creates a site.	write	`content.site.create`12 connectors
`plausible.sites.update`Update sites update	Changes a site's domain and/or tracker script settings; unspecified tracker options keep their value.	write	`content.site.update`12 connectors
`plausible.goals.list`List goals list	Lists a site's goals.	read	this connector
`plausible.stats.query`Query stats query	Runs a Stats API v2 query: metrics over a date range, optionally grouped by dimensions and filtered.	read	this connector
`plausible.goals.delete`Delete goals delete	Deletes a goal from a site.	destructive	this connector
`plausible.teams.list`List teams list	Lists the teams the account can access; api_available says whether the Sites API is enabled for each.	read	this connector
`plausible.guests.list`List guests list	Lists a site's guests and pending invitations.	read	this connector
`plausible.goals.upsert`Find or create goals upsert	Finds or creates a goal for a site.	write	this connector
`plausible.custom_props.list`List custom props list	Lists a site's custom properties.	read	this connector
`plausible.stats_v1.breakdown`List stats v1 breakdown	Breaks stats down by one property (top sources, pages, countries...).	read	this connector
`plausible.guests.delete`Delete guests delete	Removes a guest membership or invitation from a site (the user account is kept).	destructive	this connector

Try it

Prompts to paste into Claude.

Each one names the Plausible Analytics actions it will call, so you know what it reads and what it changes before you send it.

Readread
List sites list in Plausible Analytics and tell me what stands out.
callsplausible.sites.list
Writewrite
Create sites create in Plausible Analytics. Show me exactly what you will send before you save it.
callsplausible.sites.create

Governance for Plausible Analytics

Destructive actions wait for a yes.

4 Plausible Analytics actions are destructive. These are all of them:

Delete sites deleteplausible.sites.delete
Delete goals deleteplausible.goals.delete
Delete guests deleteplausible.guests.delete
Delete custom props deleteplausible.custom_props.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

doplausible.sites.deleteconfirm_policy: human

Delete sites delete?

intent: the user asked me to delete sites delete

run suspended · waiting for a named person · key plausible-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "plausible-agent",  allowed_actions: ["plausible.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "plausible.sites.delete", approver: "[email protected]" },    { match: "plausible.goals.delete", approver: "[email protected]" },    { match: "plausible.guests.delete", approver: "[email protected]" }  ]}

Illustrative. Scoped to Plausible Analytics only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Plausible Analytics costs on actionlake.

Every Plausible Analytics action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Plausible Analytics refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

1upstream call per actionall 22 Plausible Analytics actions
22actions pageeach page of a long list is one call
12reads can be cacheda cache hit costs nothing
100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Plausible Analytics action.

22 actions by area: the id your agent calls, what it does, and its effect.

Web22

plausible.custom_props.createFind or create custom props createwrite
plausible.custom_props.deleteDelete custom props deletedestructive
plausible.custom_props.listList custom props listread
plausible.goals.deleteDelete goals deletedestructive
plausible.goals.listList goals listread
plausible.goals.upsertFind or create goals upsertwrite
plausible.guests.deleteDelete guests deletedestructive
plausible.guests.listList guests listread
plausible.guests.upsertFind or create guests upsertwrite
plausible.health.getGet health getread
plausible.shared_links.upsertFind or create shared links upsertwrite
plausible.sites.createCreate sites createwrite
plausible.sites.deleteDelete sites deletedestructive
plausible.sites.getGet sites getread
plausible.sites.listList sites listread
plausible.sites.updateUpdate sites updatewrite
plausible.stats.queryQuery stats queryread
plausible.stats_v1.aggregateGet stats v1 aggregateread
plausible.stats_v1.breakdownList stats v1 breakdownread
plausible.stats_v1.realtime_visitorsGet stats v1 realtime visitorsread
plausible.stats_v1.timeseriesList stats v1 timeseriesread
plausible.teams.listList teams listread

Questions

The Plausible Analytics MCP server, answered.

Is there a Plausible Analytics MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 22 Plausible Analytics actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Plausible Analytics.

What do I need to connect Plausible Analytics?

Plausible API key. Plus your host. The free call account { op: "connections.requirements", service: "plausible" } lists exactly what to paste.

Can an AI agent delete or change things in Plausible Analytics?

Only if its key allows it, and only with an explicit confirmation. 4 Plausible Analytics actions are destructive, including delete sites delete, delete goals delete and delete guests delete. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Plausible Analytics API limit?

actionlake paces every call to the limits in the Plausible Analytics service file: 600 calls an hour per connection. Repeated reads are answered from cache (12 Plausible Analytics actions can be), which never reaches Plausible Analytics.

What does a Plausible Analytics action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (22 Plausible Analytics actions page). Cache hits, searches, dry runs and calls Plausible Analytics refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Plausible Analytics API does it cover?

The Plausible Analytics (Stats API v2 and v1, Sites API) API stats v2 / sites v1 at plausible.io by default, or the base URL set when you connect. It is built from Plausible Analytics's documentation as read on 23 October 2026. 22 actions in 1 area, each one in the signed service file (version 1.0.0).

Does actionlake keep my Plausible Analytics data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Plausible Analytics credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent Plausible Analytics today.