Skip to content
MCP server · remote

Query your measurement
data from Claude

The Serge MCP server connects your LLM client — Claude Desktop, Claude on the web, or Cursor — to your Serge workspace. Ask in plain language which AI assistants sent traffic to your site, how much of it was real buy-intent, and where sessions dropped off. The server reads your measurement data; it does not change anything.

Connection guideGitHubDeveloper hub
Jump
Connect in minutes

Mint an API key or add the connector, point your client at mcp.serge.ai, and ask your first question.

Jump
Read-only, scoped

Tools are scoped to your workspace and read your measurement data. Nothing is written or changed.

Jump
Seven measurement tools

Your client gets tools to look up sites, traffic, buy-intent split, verification, and failing sessions.

Connect your client

Two ways to authenticate. Pick one — you do not need both.

Option A — API key

Mint an API key in Settings → API keys. It starts with sk_serge_. Grant it the traffic:read scope.

Add this to your client config. The Claude Desktop config path is below; Cursor uses the same shape under its MCP settings.

macOS ~/Library/Application Support/Claude/claude_desktop_config.json
Windows %APPDATA%\Claude\claude_desktop_config.json

Restart your client. The Serge tools appear in the tool picker.

Option B — OAuth connector

In Claude, add https://mcp.serge.ai as a custom connector and sign in with your Serge account. Claude walks the OAuth flow and binds the connection to your workspace — no API key to paste or rotate.

Use this when you would rather log in than manage a key, or when you are connecting from Claude on the web.

Tools your client receives

Seven read-only tools, all scoped to your workspace. Your client picks the right one from your question.

whoami

Confirm which workspace and scopes the connection has. Call this first when a tool can't see your data.

list_sites

List the sites registered under your workspace, with their domains and IDs. Start here when you're unsure which domain a tool expects.

get_traffic_overview

Summarize AI-assistant traffic on a site over a window: sessions, platforms (ChatGPT, Claude, Perplexity, Gemini), outcomes, and top entry pages.

get_purpose_split

Split assistant sessions into buy-intent, informational, and crawler traffic, so you can tell real customer demand from bots.

get_verification_breakdown

Show, per platform, how many sessions cryptographically proved their identity versus only self-declared it.

find_failing_sessions

List sessions that abandoned a task or bounced, with the failure reason and entry/exit pages.

get_session_journey

Drill into one session — its page-by-page path, time per page, interactions, and outcome.

Scopes

An API key carries scopes that decide which tools it can call. Every tool on this page needs just one.

traffic:readRead AI-assistant traffic measurement. Required by every tool: traffic, purpose split, verification, and sessions.

Other scope keys remain grantable on older keys for data compatibility, but no live tool requires them — traffic:read covers everything on this page.

Example prompts

Paste these into your connected client. It maps each to the right tool and fills in the rest.

Which AI assistants sent traffic to yourstore.com this week?

What share of assistant traffic on yourstore.com was real buy-intent versus crawlers in the last 7 days?

Show me the sessions on yourstore.com that bounced, and where they dropped off.

Which platforms cryptographically verified their identity on yourstore.com, and which only declared it?

Troubleshooting

A tool can't see your data

Ask your client to call whoami. It returns the workspace and scopes on the connection — if the scopes are missing, mint a key with the traffic:read scope.

site_not_found

The domain isn't registered under your workspace, or you typed it differently. Ask your client to call list_sites and use a domain it returns.

How it fits with Serge

The MCP server is a read surface over the same measurement data you see in the Serge dashboard. It's the fastest way to ask a one-off question without clicking through filters.

Serge puts your ads on AI assistants — starting with ChatGPT — and tracks every click to what it returned on your site. That measurement layer is what the MCP server exposes: the sessions behind the numbers, the buy-intent split, and the journeys where visits dropped off.

Next

→ Open the step-by-step connection guide→ Open the developer hub