WebmasterID logoWebmasterID
Claude analytics integration

Claude reads your WebmasterID analytics — through MCP, with operator approval

Connect Claude Desktop, Claude Code, or the VS Code Claude extension to WebmasterID. The integration is workspace-scoped, read-only, and audit-logged by construction.

Use cases

What the Claude integration is for

The use cases below are the day-to-day shape of the workflow. Each one is a prompt the operator runs alongside the dashboard, not instead of it.

Investigate a traffic dip

Open Claude Desktop, ask why pageviews fell on /pricing last week. Claude reads the slice through MCP, returns the directional answer.

Summarise weekly AI visibility

“Summarise the AI crawlers and AI assistant referrals this week.” One prompt, one summary, audit-logged.

Pair Claude Code with the dashboard

Claude Code reads the WebmasterID Agent recommendations, opens the file in the repo mapping, prepares a diff. You review and ship.

Brief a non-technical stakeholder

Drop the conversation into a doc. The data is reproducible because Claude fetched it through MCP, not from a screenshot.

Investigate a tracker install

Ask Claude to read the recent events on a newly-configured site. Confirm the tracker is firing without opening the dashboard.

Compare two sites in your workspace

Multi-site Claude prompts work because the MCP key is workspace-scoped — one connection sees the whole portfolio.

How WebmasterID helps

Each Claude client, the same surface

The MCP server is the integration layer. Each Claude client is just a different way of talking to it.

Claude Desktop

The conversational interface for day-to-day reading and summarisation. Paste the MCP config snippet, restart the app, and the WebmasterID tools appear in the available-tools list.

Claude Code

The CLI interface for pairing analytics reads with code changes. Read Agent recommendations, open the file in the repo mapping, prepare a diff. Operator reviews and ships.

VS Code Claude extension

The editor-side interface. Useful when an investigation begins from a file or repository rather than a dashboard.

Safety model. The MCP surface is read-only. Operator approval is required for every change — there is no auto-deploy, no auto-merge, no hidden execution.

Feature

What Claude can read on your behalf

A small, deterministic surface. The same tools Claude sees are documented in the dashboard so operators always know what was read.

Traffic and events

The Event Explorer surface mirrored for AI clients. Filterable by date, type, country, pathname, referrer, session, visitor.

AI visibility

AI crawler timeline and AI assistant referrals. Useful for AI-search-era investigations.

Attribution

Directional source attribution with confidence labels. Claude can read and summarise; the operator decides.

Agent recommendations

WebmasterID Agent recommendations and the daily operator brief. Helpful for AI-assisted prioritisation.

Privacy & trust

Claude reads on your behalf — not on its own

Operators rightly worry about silent data exfiltration when AI clients connect to internal data. WebmasterID's Claude integration is built to remove that worry.

  • Workspace-scoped key

    The Bearer key Claude uses is tied to a single workspace. Cross-workspace reads are impossible.

  • Read-only

    The MCP surface has no write tools. Claude can read; the operator deploys.

  • Audit-logged

    Each read appends to the audit log. You can see exactly what Claude requested, when, and by which key.

  • Revocable

    Delete the key to terminate access. The audit log is preserved so you keep a complete history.

Questions about the Claude integration? info@helperg.com.

FAQ

Claude analytics, answered

Which Claude clients are supported?
Claude Desktop, Claude Code (CLI), and the VS Code Claude extension are supported today. Any MCP-compatible client should also work because WebmasterID exposes a standard MCP server — the /settings/mcp dashboard page ships ready-to-paste config snippets for each client.
How do I install the integration?
Sign up for WebmasterID, install the tracker on at least one site, generate a workspace-scoped API key at /settings/mcp, paste the client-specific snippet into the Claude client's MCP configuration, and restart the client. Total setup is under five minutes.
Does Claude make decisions on my behalf?
No. The MCP surface is read-only. Claude can read traffic, AI visibility, and attribution data; it can prepare prompts and propose diffs in Claude Code; it cannot deploy, cannot modify your workspace, cannot change your subscription. The operator is the executor.
Is my data sent anywhere it should not go?
No. When Claude reads WebmasterID through MCP, the request goes directly from your Claude client to our MCP endpoint. We never relay analytics to model providers, never train shared models on your data, and we never share it with third parties.
How do I revoke Claude's access?
Delete the workspace-scoped API key at /settings/mcp. The Claude client can no longer authenticate. Every read up to revocation is preserved in the workspace audit log so you have a complete record.
Does this replace the dashboard?
No. The dashboard is still the operator's primary read surface. The Claude integration is an additional channel for ad-hoc investigation, weekly summaries, and AI-assisted prioritisation — not a replacement for the curated dashboard view.