BigQuery MCP | OAuth BigQuery connector for AI agents

Tools your analytics agent reaches for on BigQuery, scoped per user.

CALL ANY TOOL

List datasets and tables, inspect schemas, run SQL queries, and monitor jobs.

bigquery_datasets_list

List datasets

List all datasets in a project the user has access to.

Parameters

Name

Type

Required

Description

project_id

string

Required

GCP project ID

max_results

integer

Optional

Max results

bigquery_tables_list

List tables

bigquery_table_schema

Get table schema

bigquery_query_run

Run query

bigquery_job_get

Get job status

Build your Agent

Drop the toolkit in, point it at the user, and your analytics agent can use BigQuery from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["bigquery"], toolNames: ["bigquery_datasets_list", "bigquery_tables_list", "bigquery_table_schema"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["bigquery"], toolNames: ["bigquery_datasets_list", "bigquery_tables_list", "bigquery_table_schema"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["bigquery"], toolNames: ["bigquery_datasets_list", "bigquery_tables_list", "bigquery_table_schema"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/bigquery",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using BigQuery.

Search & schema

Copy the prompt

Copied

List all datasets in [project].

Copy the prompt

Copied

Show me the schema of [dataset.table].

Copy the prompt

Copied

Which tables are in [dataset]?

Copy the prompt

Copied

How large is [table_id] right now?

Query & analysis

Copy the prompt

Copied

Run: SELECT date, COUNT(*) FROM events.signups GROUP BY date.

Copy the prompt

Copied

Top 10 customers by revenue this quarter.

Copy the prompt

Copied

Daily active users for the last 30 days.

Copy the prompt

Copied

Failed payment count by gateway last week.

Monitoring & cost

Copy the prompt

Copied

Which queries scanned more than 100GB today?

Copy the prompt

Copied

Job status for [job_id].

Copy the prompt

Copied

Slowest queries in the last hour.

Copy the prompt

Copied

Cost by user for the current month.

SEE HOW AUTH WORKS

Users authorize BigQuery once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

BigQuery

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

BigQuery

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

BigQuery

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

BigQuery

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other analytics agents and MCP connectors. Working code, live demos, fork what fits.

GTM

HubSpot to Slack updates agent

Watch HubSpot deal stage changes and post structured updates to the right Slack channel. Reps stop checking the CRM all day.

HubSpot

Slack

View agent

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Queries bypass IAM and row-level security

A shared BigQuery service account looks fine in a demo. In production, every query runs with elevated permissions that bypass IAM roles, dataset-level access, and row-level security. Scalekit resolves the actual user's token so every query respects their real permissions.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

BigQuery today. Snowflake, Redshift, Databricks tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit

Frequently Asked Questions

Does the agent access BigQuery as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the BigQuery oauth 2.0 stored?

Can I limit what the agent is allowed to do in BigQuery?

What happens when a user revokes BigQuery access?

Can the agent query datasets the user lacks access to?

Start in your coding agent

Up and running in one command

Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up

Claude Code REPL

Copy Copied

/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack

Cursor Code REPL

Copy Copied

# ~/.cursor/mcp.json
{
""mcpServers"": {
""bigquery"": {
""url"": ""https://mcp.scalekit.com/bigquery"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}

Codex Code REPL

Copy Copied

# ~/.codex/config.toml
[mcp_servers.bigquery]
url = ""https://mcp.scalekit.com/bigquery""
auth_env = ""SCALEKIT_TOKEN""

Copilot Code REPL

Copy Copied

# .vscode/mcp.json
{
""servers"": {
""bigquery"": {
""url"": ""https://mcp.scalekit.com/bigquery"",
""type"": ""http""
}
}
}