Documentation

MCP server (AI tools)

Splitlab runs a Model Context Protocol (MCP) server. Connect it to an AI tool and you can ask questions about your workspace in plain language: which test is winning, how revenue per visitor moved this week, or whether attribution is healthy.

Server URLhttps://mcp.splitlab.io/mcp
TransportStreamable HTTP
Sign-inOAuth 2.1 (most clients), or a workspace API key sent as a Bearer header
AccessRead-only, one workspace per connection

Availability

The MCP server is rolling out gradually. If you don't see Connect AI tools under Workspace settings → API keys, contact Splitlab support to have it switched on.

What it can and cannot do

  • Read-only. No tool creates, changes, pauses or deletes anything. An AI tool can't start a test, edit a variant or change traffic.
  • One workspace. When you sign in, you choose the workspace the connection can read. It never reaches your other workspaces. Connect again to use a different one.
  • No lead or payment data. Individual leads, contact details and billing are not exposed.

Tools

ToolWhat it returns
whoamiThe signed-in user and the workspace this connection can read
get_workspaceWorkspace name, website and reporting settings
list_campaignsTests in the workspace, with status and type
get_campaignOne test's name, type, status, page URL and dates
get_campaign_reportPer-metric variant stats, statistical significance and revenue
get_metric_detailThe full breakdown of one metric in a test
get_timeseriesConversion rate, revenue, expected improvement and visitors per day
get_campaign_timelineWhen a test was started, paused, edited or ended
check_attribution_healthWhether conversions and revenue are being attributed to variants
get_kpi_overviewHeadline numbers across the workspace
searchSearches tests by name (the shape ChatGPT expects)
fetchReturns one search result in full (the shape ChatGPT expects)

Connect your AI tool

You'll find the same instructions, with copy buttons and one-click install links, in Splitlab under Workspace settings → API keys → Connect AI tools.

Every client below signs in with OAuth: the first time it connects, your browser opens Splitlab, you sign in, choose the workspace and approve.

Claude (claude.ai and Claude Desktop)

  1. Open Settings → Connectors.
  2. Choose Add custom connector and paste https://mcp.splitlab.io/mcp.
  3. Select Connect, then sign in to Splitlab and approve access.

Claude Code

claude mcp add --transport http splitlab https://mcp.splitlab.io/mcp

Then start Claude Code and run /mcp to sign in.

ChatGPT

  1. In ChatGPT settings, turn on Developer mode. It is under Apps & Connectors → Advanced settings, or under Security on some accounts. It needs a paid plan, and on work accounts an admin may have to allow it.
  2. Choose Create, name it Splitlab, paste https://mcp.splitlab.io/mcp and choose OAuth authentication.
  3. Save, then sign in to Splitlab and approve access.

Cursor

Add Splitlab to Cursor with one click, or add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "splitlab": {
      "url": "https://mcp.splitlab.io/mcp"
    }
  }
}

VS Code (GitHub Copilot)

Add Splitlab to VS Code with one click, or add this to .vscode/mcp.json in your project:

{
  "servers": {
    "splitlab": {
      "type": "http",
      "url": "https://mcp.splitlab.io/mcp"
    }
  }
}

Copilot uses MCP tools in Agent mode.

Gemini CLI

gemini mcp add --transport http splitlab https://mcp.splitlab.io/mcp

Or add the server to ~/.gemini/settings.json:

{
  "mcpServers": {
    "splitlab": {
      "httpUrl": "https://mcp.splitlab.io/mcp"
    }
  }
}

Then start Gemini CLI and run /mcp auth splitlab to sign in.

Windsurf

Add this to ~/.codeium/windsurf/mcp_config.json, then refresh the MCP servers in Cascade:

{
  "mcpServers": {
    "splitlab": {
      "serverUrl": "https://mcp.splitlab.io/mcp"
    }
  }
}

Other clients

Point any MCP client that supports Streamable HTTP at https://mcp.splitlab.io/mcp. If it supports OAuth, it discovers the sign-in flow on its own. If it doesn't, use an API key.

Use an API key instead of OAuth

For clients that can't sign in with OAuth, or for scripts:

  1. In Splitlab, open Workspace settings → API keys and click Create key.
  2. Copy the key. It starts with sl_ and is shown once.
  3. Configure your client to send it on every request:
Authorization: Bearer sl_your_key_here

A key reads only the workspace it was created in. Revoke it from the same page and any client using it loses access immediately.

Troubleshooting

SymptomWhat to do
401 UnauthorizedThe sign-in expired or was revoked, or the API key is wrong or revoked. Reconnect the client (in Claude Code, run /mcp; in Gemini CLI, /mcp auth splitlab), or create a new key
The Splitlab MCP server is not enabled (503)The MCP server isn't switched on yet. Contact Splitlab support
429 Too Many RequestsEach credential can make 120 requests per minute, and each network address 300. Wait a minute and try again
The AI tool sees the wrong workspaceEach connection reads one workspace. Disconnect and connect again, choosing the other workspace