Asemic exposes an MCP server (Model Context Protocol, the open standard AI assistants use to call external tools). Connect it once, and you can ask analytics questions in the AI chat you already use:

“What was ARPDAU by payment segment last week, and how does it compare to the week before?”

The AI discovers your project’s metrics and dimensions, runs the query through Asemic, and narrates the result. It can render charts, find and read existing dashboards and stories, hand you a link to open them in Asemic, and, when your role allows it, build and edit dashboards and add annotations from the conversation.

The reason the answers are trustworthy: the AI does not write SQL against raw tables. It queries the named, versioned metric definitions in your semantic layer, so the numbers in chat match the numbers on your dashboards, whoever asks.

Works with claude.ai (custom connectors), Claude Desktop, Claude Code, ChatGPT (Developer mode), Gemini CLI, and any MCP-capable client.

The same instructions live in the product: open Settings, then the “Connect AI” tab. It shows your server URL ready to copy, setup steps per assistant (Claude, ChatGPT, Gemini), and your personal access tokens.

Connect from claude.ai or Claude Desktop

In claude.ai, open Settings, then Connectors, then select “Add custom connector”.
Paste the server URL: https://app.asemicanalytics.com/mcp
The browser opens Asemic’s sign-in (your regular Asemic credentials or Google sign-in), followed by a permission screen listing what the connection may do:
- “Discover metrics and dashboards, run analytics queries, render charts”
- “Create and edit dashboards and stories”
Select “Authorize”. The chat can now use the Asemic tools.

A few things worth knowing:

No API key is created or pasted anywhere in this flow; registration and sign-in are automatic (OAuth).
Access is per user: the AI sees exactly the projects you can see, and its write tools follow your role: any member’s assistant can create private dashboards, while publishing and annotating require Editor or above.
After Asemic ships new tools, claude.ai can keep serving a cached tool list; removing and re-adding the connector refreshes it.

Connect from ChatGPT

ChatGPT supports custom MCP connectors on paid plans (Plus, Pro, Business, Enterprise, Edu) with Developer mode enabled:

In ChatGPT on the web, open Settings, then Apps, then “Advanced settings”, and enable “Developer mode”.
Back in Apps, select the create option and give the connector a name, for example “Asemic”.
Enter the server URL: https://app.asemicanalytics.com/mcp
Under Authentication, choose OAuth. ChatGPT discovers Asemic’s sign-in automatically; the same Asemic permission screen appears as in the claude.ai flow.
Authorize, then enable the connector in the conversations where you want it.

OpenAI moves this UI around occasionally; if the menus differ, look for the custom connector or app creation option behind Developer mode.

Connect from Gemini CLI

The consumer Gemini app does not accept custom MCP connectors today; Google’s supported path is Gemini CLI. Add Asemic to ~/.gemini/settings.json:

{
  "mcpServers": {
    "asemic": {
      "httpUrl": "https://app.asemicanalytics.com/mcp",
      "oauth": { "enabled": true }
    }
  }
}

Gemini CLI discovers Asemic’s OAuth configuration automatically and opens the sign-in in your browser. If sign-in does not start on its own, run /mcp auth asemic inside the CLI. A personal access token also works instead of OAuth: replace the oauth entry with "headers": { "Authorization": "Bearer <your-token>" }.

Connect from Claude Code

Power users connect with a personal access token instead of the OAuth flow:

In Asemic, create a token under “Personal Access Tokens” (in Settings, “Connect AI” tab, or in your profile settings).
Add the server:

claude mcp add --transport http asemic https://app.asemicanalytics.com/mcp \
  --header "Authorization: Bearer <your-token>"

Tokens are revocable from the same settings page.

What you can ask

“What metrics do we track?”
“Show DAU for the last 30 days, split by platform.”
“Compare ARPDAU this month vs last month for payers only.”
“What does our retention curve look like for the June cohorts?”
“Do we have a dashboard about monetization? Link me to it.”

Shape it to your team

The assistant works out of the box, but you can make it speak your team’s language and run your team’s recurring analyses. Custom instructions (“when I say active users, use DAU”) and saved prompts (“run the weekly monetization check”) are set on the “AI Assistant” settings tab, scoped to you, a project, or the whole workspace. See Customize the assistant.

Tool reference

These names appear in your chat client’s tool list:

Tool	What it does
`list-projects`	Lists the projects you can query.
`list-metrics`	Lists a project’s metrics with descriptions and units, and whether each plots over calendar dates, days since install (cohort), or both.
`list-dimensions`	Lists the user properties available for grouping and filtering.
`get-dimension-values`	Lists the distinct values of one dimension (for exact filters).
`run-query`	Runs a query: one or more metrics over a date range, optionally grouped by dimensions, filtered, and compared against the previous period. Returns a compact table plus totals.
`chart-query`	Same inputs as `run-query`, but returns a finished, Asemic-styled interactive chart the assistant can present.
`list-dashboards`	Lists dashboards and stories in a project, with links.
`get-dashboard`	Reads one dashboard or story: its charts, settings, and story text.
`render-chart` / `render-dashboard`	Renders an existing chart or dashboard to an image, pixel-identical to the app.
`list-annotations`	Reads the annotations in a date range.
`list-saved-prompts` / `run-saved-prompt`	Lists and runs your team’s saved prompts: reusable, named analyses.

Write tools, gated by role:

Tool	What it does
`create-dashboard` / `clone-dashboard`	Creates a dashboard, or clones one you can view. New content starts private to you.
`update-dashboard` / `delete-dashboard`	Edits or deletes dashboards you are allowed to manage.
`add-chart` / `update-chart` / `remove-chart`	Edits the charts on a dashboard.
`add-text-block` / `update-text-block`	Edits a dashboard’s text blocks.
`set-dashboard-sharing`	Publishes or unpublishes a dashboard (Editor and above).
`create-annotation`	Adds a release, campaign, or incident annotation (Editor and above).

How the AI behaves

Results are capped (default 200 rows). The AI is told when a result was truncated and how to narrow the query, so you may see it refine its own query; that is expected.
Daily metrics plot over calendar dates; cohort metrics plot over days since install. The AI is told which is which, so questions like the retention example work naturally.
If a query is invalid (unknown metric, bad filter), the AI receives a precise error and corrects itself. This is normal and visible in the chat’s tool log.

Security and privacy

Sign-in uses your existing Asemic account, and the permission screen is shown before any access.
The AI cannot change the data model, warehouse connections, or settings through this integration. Dashboard and annotation writes follow the same role rules as the app: nothing the assistant does exceeds what its user could do by hand.
Queries run on demand against the project’s published model; raw event data is not copied to the AI provider beyond the query results shown in chat.
Access tokens expire and refresh automatically (OAuth), or are revocable personal tokens on the Claude Code path.