Connect BigQuery MCP to your AI Agents
Query petabytes of BigQuery data in plain English.
Everything you can ask your agent about your BigQuery data.
Ask in plain English — Sequel translates it into a BigQuery query, runs it, and your agent hands back the answer. No SQL, no dashboards, no CSV exports.
Connect to your agent- What are the top 10 events by count this week?
- Show me daily revenue for the past 30 days as a line chart
- Which users had the highest session count last month?
- What's the p95 query latency by dataset over the past 7 days?
- List all tables in my analytics dataset with row counts
Install
Install BigQuery MCP in your agent
Pick your app and Sequel installs itself: a one-click link where the client supports it, that client’s own few steps where it doesn’t. Every route signs in with your Sequel account over OAuth, so there is no API key to copy and nothing to keep in sync.
Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex, Grok, Muse, dots and any other MCP app
Already have an MCP client?
https://api.sequel.sh/mcp
Add it as a remote (streamable HTTP) server and sign in when prompted. Skills come with it; nothing else to install. Manual setup per client
Choose your app
Claude
One click, opens in the app
Cursor
One click, opens in the app
VS Code
One click, opens in the app
ChatGPT
Turn on developer mode, then add Sequel. About two minutes.
Claude Code
Run one command, then sign in with /mcp.
Codex
Run one command, then sign in.
Gemini CLI
Run one command, then sign in with /mcp auth.
Grok
Add Sequel as a connector and sign in.
Grok Bot
Paste this to the bot. It registers Sequel and asks you to sign in.
Muse
Muse writes its own connector. One message is the whole setup.
dots
Add Sequel in ChatGPT; your dot picks it up with no extra step.
OpenCode
Add Sequel as a remote server from the OpenCode CLI.
Other MCP app
Any client that speaks remote MCP can connect with this URL.
AI agents
Connect BigQuery MCP to your favorite AI agent
Claude
Use Claude to query your databases, explore schemas, and build analyses — all from one conversation.
Cursor
Query your databases and explore schemas without leaving your code editor.
ChatGPT
Connect ChatGPT to your databases and get data-backed answers in every conversation.
VS Code
Get database access inside VS Code Copilot without leaving your editor.
Windsurf
Give Windsurf's Cascade AI access to your databases — query data without leaving your editor.
Zed
Connect Zed's AI assistant to your databases for real-time data access while you code.
Gemini
Connect Google Gemini to your databases for grounded, data-backed answers.
Claude Code
Query your databases directly from the Claude Code CLI — without leaving your terminal.
Codex
Give OpenAI Codex CLI real-time database access for data-grounded coding sessions.
OpenClaw
Turn your self-hosted OpenClaw agent into a data analyst that queries every source you've connected.
Hermes
Give Nous Research's Hermes agent read access to every database and marketing tool you've connected.
Grok Bot
Tell your Grok bot to add Sequel and it can query every database and marketing tool you've connected.
Muse
Give Meta's Muse one message and it builds its own connector to every source you've put in Sequel.
dots
Add Sequel once in ChatGPT and your dot can answer data questions on its own, day and night.
Skills
Playbooks that run on BigQuery
Step-by-step procedures your agent follows on your BigQuery data, instead of improvising a query. Browse all skills
Can we trust our product metrics
Two tools show different numbers for the same metric and nobody knows which to trust. Reconciles the disputed figure against a system of record such as Stripe or the application database, then finds the instrumentation defect behind it: duplicate and near-duplicate event names, events that silently stopped firing, missing properties and system-fired events counted as user actions.
Feature launch impact readout
Measure whether a feature we just shipped actually landed: adoption against an eligible denominator of users who could even reach it, breadth, depth and sustained use after the release, a pre and post impact estimate with or without a control group, and a keep, iterate or sunset call.
Find our activation moment
Discover the aha moment: which early in-product action, taken in the first session or first week, most separates users who stay from users who vanish, how to score candidate first actions by retention lift, and what share of new signups ever reach it. Covers activation metric definition, activation rate and time to value.
Is our retention curve flattening
Do users keep coming back, or do they drift away after the first week or month? Builds the cohort retention curve for your key action at its natural frequency and judges whether it flattens to a plateau or decays to zero, covering N-day versus unbounded retention, repeat usage, leaky bucket diagnosis and how the plateau compares to published benchmarks.
Read out an A/B test honestly
Is this A/B test result real, or statistically significant only by accident? Runs the validity gates before reporting anything (sample ratio mismatch, peeking, power and minimum detectable effect, novelty), then gives absolute and relative lift with a confidence interval, a ship or kill call, and the winning variant extended through to revenue instead of stopping at the proxy metric.
Analyze BigQuery data alongside…
PostgreSQL
Query your PostgreSQL database in plain English. No SQL required.
MySQL
Instant insights from your MySQL database. Ask in plain English.
ClickHouse
Real-time analytics on ClickHouse at any scale, in plain English.
Google Sheets
Query, write, and manage Google Sheets with AI.
Google Analytics 4
Ask your GA4 data anything. No SQL, no dashboards.
Google Search Console
Unlock your SEO data with natural language. No exports, no pivot tables.
MCP Server
Connect any MCP-compatible server and query it with AI in seconds.
Stripe
Ask your Stripe data anything. MRR, churn, refunds — answered in plain English.
Polar
Ask your Polar revenue, subscriptions, and usage data anything — in plain English.
Dodo Payments
Ask questions about payments, subscriptions, refunds and payouts in plain English.
PostHog
Ask your PostHog product data anything — with HogQL under the hood.
Mixpanel
Conversational analytics on your Mixpanel events, funnels, and retention.
Amplitude
Query your Amplitude taxonomy, funnels, and dashboards in plain English.
HubSpot
Your AI analyst for HubSpot contacts, deals, tickets, and pipelines.
Ahrefs
Ask your Ahrefs SEO data anything: backlinks, keywords, and traffic.
Apollo.io
Ask your Apollo.io prospects, contacts, and accounts anything, in plain English.
Cloudflare D1
Ask your Cloudflare D1 database questions in plain English.
Instagram organic analytics — post engagement, reach, and audience insights in plain English.
Frequently asked questions
Do I need a service account key to connect BigQuery?
No. Sequel uses Google OAuth 2.0, so you authorize with your Google account directly — no JSON key files required. Sequel requests read-only access (bigquery.readonly scope) so it can only run SELECT queries.
What is a GCP Project ID and where do I find it?
The GCP Project ID is the unique identifier for your Google Cloud project (e.g. my-company-analytics-123). You can find it in the Google Cloud Console at the top of the dashboard, or by running `gcloud config get-value project` in your terminal.
Does Sequel support BigQuery legacy SQL?
No. Sequel generates standard SQL (GoogleSQL) only. Legacy SQL is deprecated by Google and is not supported.
Will Sequel see all my BigQuery datasets and tables?
Sequel will list all datasets your Google account has access to within the connected project. You can restrict schema introspection to specific datasets from the connection settings after connecting.
Are there query cost implications?
Yes — BigQuery charges for bytes scanned per query. Sequel generates efficient queries, but on very large tables you may want to apply partition filters. You can add instructions in the connection settings to guide the AI to always filter by partition columns.
Start analyzing your BigQuery data today
Connect in minutes — then ask across all your data, not just one source.