QuickBooks

Live

OAUTH 2.0

ACCOUNTING

Accounting & Finance

Every invoice, payment, and financial report your team manages lives in QuickBooks. QuickBooks MCP gives your agent authenticated access to accounting data scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the QuickBooks account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: Permissions enforced. 90-day audit trail.
QuickBooks
agent · Acme Q3
Run
Which invoices are overdue by more than 30 days and what is the total outstanding?
S
qb_invoices_list
81ms
Finance agent
8 invoices overdue 30+ days. Total outstanding: $42,800. Largest: Initech Corp ($12,400, 47 days). 3 customers have multiple overdue invoices. Recommend escalation for Initech and Umbrella LLC.
Sources: QuickBooks AR, overdue 30+ days
quickbooksmcp
8 invoices
18:29
Message Claude...

Tools your finance agent reaches for on QuickBooks, scoped per user.

CALL ANY TOOL
List and inspect invoices, browse customers, pull P&L reports, and review the chart of accounts.
qb_invoices_list
List invoices
List QuickBooks invoices with status, customer, and date filters.
Parameters
Name
Type
Required
Description
status
string
Optional
Filter: open, paid, overdue, void
customer_id
string
Optional
Customer filter
date_from
string
Optional
Start date: YYYY-MM-DD
limit
integer
Optional
Max invoices
qb_invoice_get
Get invoice
qb_customers_list
List customers
qb_profit_loss
Get P&L report
qb_accounts_list
List accounts
Build your Agent
Drop the toolkit in, point it at the user, and your finance agent can use QuickBooks 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: ["quickbooks"], toolNames: ["qb_invoices_list", "qb_invoice_get", "qb_customers_list"] },
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: ["quickbooks"], toolNames: ["qb_invoices_list", "qb_invoice_get", "qb_customers_list"] },
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: ["quickbooks"], toolNames: ["qb_invoices_list", "qb_invoice_get", "qb_customers_list"] },
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/quickbooks",
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 QuickBooks.
Invoices & AR
Copy the prompt
Copied
List all overdue invoices.
Copy the prompt
Copied
Get details for invoice [id].
Copy the prompt
Copied
Which customers have unpaid invoices over $10K?
Copy the prompt
Copied
Invoices sent this month with no payment.
Reports
Copy the prompt
Copied
Profit and loss for Q4 [year].
Copy the prompt
Copied
P&L summary by month for this year.
Copy the prompt
Copied
Total revenue recognized this quarter.
Copy the prompt
Copied
Expense breakdown by account last month.
Customers & accounts
Copy the prompt
Copied
List all customers with outstanding balances.
Copy the prompt
Copied
Get the chart of accounts.
Copy the prompt
Copied
Which expense accounts had the most activity this month?
Copy the prompt
Copied
Customers with overdue invoices over 60 days.
SEE HOW AUTH WORKS
Users authorize QuickBooks once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
QuickBooks
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
2
Store
Their
QuickBooks
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
3
Resolve
When your agent calls a
QuickBooks
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
4
Audit
Every
QuickBooks
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 finance agents and MCP connectors. Working code, live demos, fork what fits.
GTM
Salesforce customer insights agent
Surface Salesforce account activity, NPS signals, and renewal flags into Slack threads for the account team.
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.
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.
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.
QuickBooks 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 access QuickBooks 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 QuickBooks oauth 2.0 stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in QuickBooks?
Yes. Pass a tool name filter to listScopedTools so the finance agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches QuickBooks.
What happens when a user revokes QuickBooks access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent access multiple QuickBooks companies under one connection?
No. Each QuickBooks OAuth connection maps to a single company file. Multi-company access requires a separate connected account per company. The agent cannot switch company contexts within one connection.
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
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""quickbooks"": {
""url"": ""https://mcp.scalekit.com/quickbooks"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.quickbooks]
url = ""https://mcp.scalekit.com/quickbooks""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""quickbooks"": {
""url"": ""https://mcp.scalekit.com/quickbooks"",
""type"": ""http""
}
}
}