Connector guide2-minute read4 MCP toolsEnglish · Deutsch · Italiano

How to Connect Vercel Analytics to ChatGPT — via MCP

Read Vercel Analytics / Speed Insights / Audience data via the Vercel API. 4 tools, Bearer auth.

HCBy HelpCode teamUpdated 2 min read Open source on GitHub

No credit card · 7-day trial · Self-host alternative available

MCP connector

Vercel Analytics

Read Vercel Analytics / Speed Insights / Audience data via the Vercel API. 4 tools, Bearer auth.

Tools

4

Region

INTL

Category

analytics

Authentication

Required env vars

VERCEL_ACCESS_TOKEN
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Source-available BSL-1.1
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

No install? Use cloud.anythingmcp.com directly.

Sign in, install the Vercel Analytics in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.

Open Cloud

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Vercel Analytics, paste your credentials, mint an MCP API key — done. No Docker, no git clone, no local server.

Vercel Analytics + ChatGPT

Read Vercel Analytics / Speed Insights / Audience data via the Vercel API. 4 tools, Bearer auth.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

VERCEL_ACCESS_TOKEN

Step 1 — Get credentials

com/docs/rest-api).

Setup:

  1. Sign in to https://vercel.com → top-right avatar → Settings → Tokens → Create Token.
  2. Pick scope (account-level or team-level). Set VERCEL_ACCESS_TOKEN.
  3. For team-scoped queries also set VERCEL_TEAM_ID (visible in Team Settings).

Authentication: Authorization: Bearer ${VERCEL_ACCESS_TOKEN}.

Note: Vercel's Web Analytics + Speed Insights data endpoints went through major changes in 2024-2025. Some endpoints are paywall/plan-gated. The adapter uses the stable public endpoints; some analytics queries require Pro+ plan.

Pagination: cursor-based via until Unix ms (return items older than this).

…(continued in the in-app connector instructions)

Step 2 — Install the adapter

git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d

Step 3 — Add the connector in ChatGPT

ChatGPT supports MCP servers via the Connectors feature (Plus / Pro / Team / Enterprise plans). The free tier does not support custom connectors.

  1. Open ChatGPT → Settings → Connectors (or click the 🔧 icon in the composer → Manage connectors).
  2. Click "Add custom connector".
  3. Fill in:
    • Name: Vercel Analytics
    • MCP server URL: https://cloud.anythingmcp.com/mcp
    • Authentication: Bearer token → paste your MCP API key (from AnythingMCP → Profile → MCP API Keys → New Key)
  4. Click Connect to authorize.

Available tools

ToolWhat it does
vercel_analytics_get_userReturn the user the token belongs to
vercel_analytics_list_projectsList projects in the team / account
vercel_analytics_get_deploymentsList deployments for a project
vercel_analytics_get_speed_insightsGet Speed Insights (Core Web Vitals) data for a project — requires Vercel Speed Insights enabled on the project + Pro plan

FAQ

Does ChatGPT free tier work with custom MCP connectors? No — Plus, Pro, Team or Enterprise required.

Next steps

Ready to ship

Your Vercel agent is one click away.

Install the connector, paste the key, prompt ChatGPT. Free for 7 days, no credit card.