BigQuery MCP connector
The BigQuery connector lets Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent run queries, browse datasets and check jobs in BigQuery as the signed-in person, with every call written to an audit log.
- Connects over OAuth
- Free 14-day trial
- No credit card
Run last month's revenue by region query and summarize the results
Working in BigQuery with Elaichi
-
Get single BigQuery dataset by ID
-
List all BigQuery datasets
-
Get single BigQuery job by ID
How to connect BigQuery to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
BigQuery MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
BigQuery MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
BigQuery MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web. The plugin directory lives at chatgpt.com/plugins.
BigQuery MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
BigQuery MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect BigQuery to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
What teams do with BigQuery through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in BigQuery is logged.
-
Analytics
Answer a data question without writing SQL
Ask for last quarter's orders by region in plain words, let the agent run the query in BigQuery, and read the result back in the same chat.
-
Finance
Pull month-end numbers from the warehouse
Run the revenue query against the finance dataset, get the result, and have it summarized for the close meeting without waiting on an analyst.
-
Marketing
Check campaign results in a dataset
List the datasets in the marketing project, run a query on last week's campaign table, and get the numbers before the standup.
-
Data engineering
Find out why a job is still running
List the jobs in a project, open the one that has been running for an hour, and cancel it if it is stuck.
-
Security
See who can run a routine
Look up the access policy on a routine, check whether a given account has permission, and tidy up policies that have drifted.
-
Operations
Set up a dataset for a new project
Create a dataset, give it a description, and later update or restore it, all without opening the BigQuery console.
Try asking
- “Run last month's revenue by region query and summarize the results”
- “Which BigQuery jobs are still running right now?”
- “List the datasets in the marketing project”
What connecting BigQuery gets you
6 screens from Elaichi, each doing one job for your BigQuery account.
Ask Elaichi to work across your apps.
Run last month's revenue by region query and summarize the results
Which BigQuery jobs are still running right now?
List the datasets in the marketing project
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask BigQuery a question in plain English.
Type what you want to know and get an answer from live datasets, not a dashboard.
Copy the endpoint
AI apps
One endpoint brings BigQuery to every AI client.
Claude, ChatGPT and Cursor share one governed endpoint, with no SDK and no shared API key.
Tool catalog
47 BigQuery tools, ready without writing any code.
Datasets, jobs, queries, models and routines, covered the moment BigQuery is connected.
Toolboxes
Every team gets its own BigQuery toolbox.
Analysts query, engineers manage jobs, and each team sees only the toolbox scoped to it.
Shared connections
Share BigQuery access, never the credential.
One person connects BigQuery, shares it with teams, and nobody else handles a secret.
Audit log
Every BigQuery query is on the record.
When, who, what happened and which dataset, in an append-only log you can search.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
BigQuery digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch datasets
BigQuery
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Jake Morgan
Approve Deny -
Post the digest
BigQuery
Queued
Workflows
A schedule runs the BigQuery digest for you.
Jobs are fetched, grouped and drafted into a digest a person approves before it posts.
BigQuery health
Refreshed 4 minutes ago · every 15 minutes · from the datasets collection
Datasets
1,284 ↓ 12%
Jobs
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Datasets created
Last 14 days
By team
Share of activity
Analytics 34%
Finance 27%
Marketing 21%
Data platform 18%
Collections and dashboards
BigQuery health, computed without a model.
Four metrics, fourteen days of jobs created and a breakdown by team, refreshed on schedule.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for BigQuery
All three can connect BigQuery to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over BigQuery tools | Allow or restrict single BigQuery tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per BigQuery call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
BigQuery tools for your AI agents
47 tools are ready to call through Elaichi's MCP endpoint the moment you connect BigQuery, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
Questions, answered
How do I connect BigQuery to Claude?
Connect BigQuery in Elaichi first, then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. BigQuery is one of the applications where you register an OAuth application in your own Google Cloud project once and paste its client ID and secret into Elaichi; after that, nobody else on the team needs them. Each person then sees the normal Google sign-in screen and approves access to BigQuery as themselves.
Does BigQuery work with ChatGPT and Cursor as well as Claude?
Yes. Once BigQuery is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect BigQuery once and every client picks it up.
What can an AI agent actually do with my BigQuery data?
An agent can run a query in BigQuery and read the result back to you, list your projects and datasets, create or update a dataset, and check on jobs, including cancelling one that is stuck. It can also list the models in a project and look up who has permission to use a routine. Short, concrete asks such as 'run the churn query for March' work better than long paragraphs.
Does connecting BigQuery give the AI every dataset in my project?
No. Every call to BigQuery runs as the person who signed in, so an agent can only see the projects, datasets and jobs that person already has access to in BigQuery. Elaichi can narrow that further with roles and restrictions, but it never widens it.
Can I stop an agent from deleting or changing things in BigQuery?
Yes. Restrictions in Elaichi work per action, so you can restrict deleting a BigQuery dataset, deleting a routine or cancelling a job for a role or for one person, while leaving queries open. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.
What happens to a BigQuery connection when someone leaves?
Offboarding a person in Elaichi ends their access to BigQuery through every client at once. A shared BigQuery connection keeps working for everyone else on the team. If you disconnect BigQuery in Elaichi, it disappears from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client in one step.
Does the BigQuery MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. BigQuery is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for BigQuery?
Yes. Both let Claude, ChatGPT or Cursor use BigQuery. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every BigQuery call.
How is Elaichi different from Composio for BigQuery?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to BigQuery: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put BigQuery in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot