BigQuery (Service Account) MCP for AI agents

Tools your analytics agent reaches for on BigQuery (Service Account), enforced by service account IAM.

CALL ANY TOOL

List datasets and tables, inspect schemas, run SQL queries, stream rows, and monitor jobs — all under service account IAM.

bigqueryserviceaccount_cancel_job

Cancel Job

Request cancellation of a running BigQuery job. Returns the final job resource. Cancellation is best-effort and the job may complete before it can be cancelled.

Parameters

Name

Type

Required

Description

job_id

string

Required

The ID of the job to cancel

location

string

Optional

Geographic location where the job was created, e.g. US or EU

bigqueryserviceaccount_dry_run_query

Query dry run

bigqueryserviceaccount_get_dataset

Get Dataset

bigqueryserviceaccount_get_job

Get Job

bigqueryserviceaccount_get_model

Get Model

bigqueryserviceaccount_get_query_results

Get Query Results

bigqueryserviceaccount_get_routine

Get Routine

bigqueryserviceaccount_get_table

Get Table

bigqueryserviceaccount_insert_query_job

Insert Query Job

bigqueryserviceaccount_list_datasets

List Datasets

bigqueryserviceaccount_list_jobs

List Jobs

bigqueryserviceaccount_list_models

List Models

bigqueryserviceaccount_list_routines

List Routines

bigqueryserviceaccount_list_table_data

List Table Data

bigqueryserviceaccount_list_tables

List Tables

bigqueryserviceaccount_run_query

Query run

Build your Agent

Drop the toolkit in, configure the service account once, and your analytics agent can query BigQuery from the first run.

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: ["bigqueryserviceaccount"], toolNames: ["bqsa_datasets_list", "bqsa_table_schema", "bqsa_query_run"] },
  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 });

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: ["bigqueryserviceaccount"], toolNames: ["bqsa_datasets_list", "bqsa_table_schema", "bqsa_query_run"] },
  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: ["bigqueryserviceaccount"], toolNames: ["bqsa_datasets_list", "bqsa_table_schema", "bqsa_query_run"] },
  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 }],
});

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/bigqueryserviceaccount",
    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 querying BigQuery via service account.

Schema & discovery

Copy the prompt

Copied

List all datasets in [project].

Copy the prompt

Copied

Show the schema of [dataset.table].

Copy the prompt

Copied

Which tables are in [dataset]?

Copy the prompt

Copied

How many rows are in [table_id]?

Query & analysis

Copy the prompt

Copied

Run: SELECT DATE(event_time), COUNT(*) FROM events.signups GROUP BY 1.

Copy the prompt

Copied

Monthly active users by tier for the last 6 months.

Copy the prompt

Copied

Top 10 accounts by revenue this quarter.

Copy the prompt

Copied

Daily churn rate for the last 30 days.

Monitoring & ops

Copy the prompt

Copied

Which queries scanned the most data today?

Copy the prompt

Copied

Job status for [job_id].

Copy the prompt

Copied

List tables updated in the last 24 hours.

Copy the prompt

Copied

Estimated cost for query: [SQL].

SEE HOW AUTH WORKS

Configure a GCP service account once. Scalekit vaults the key, resolves it at request time, and logs every call with the service account identity.

Authorize

Your user connects

BigQuery (Service Account)

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 (Service Account)

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 (Service Account)

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 (Service Account)

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 vault-and-enforce 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 identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// 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 (Service Account) today. Others 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

FAQs

Frequently Asked Questions

Does the agent use a service account or a user credential?

A service account. Unlike OAuth connectors, no user authorization flow is required. A GCP service account key is configured once by an admin and vaulted in Scalekit. Every call runs under that service account identity.

Where is the BigQuery (Service Account) service account stored?

In Scalekit's managed AES-256 token vault. The JSON key file is never stored on disk or passed to the LLM. Rotation is a single vault update. The key never appears in prompts, logs, or agent context.

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

Yes. Pass a tool name filter to listScopedTools so the analytics agent only sees the subset you authorize. Additionally, scope the service account IAM role to the minimum datasets required — Scalekit enforces both layers.

What happens if the service account key is rotated?

Update the key in the Scalekit vault. No code changes required. Subsequent calls resolve the new key automatically. The old key can be disabled in GCP immediately after the vault update. The event is logged for audit.

Does the agent respect BigQuery IAM, dataset ACLs, and row-level security?

Yes. All queries run under the service account IAM role. Dataset-level access, table ACLs, column-level security, and row-level security policies all apply. The agent cannot read or write what the service account is not granted.

On this page

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