Gusto MCP Connector for AI Agents

Tools your hr agent reaches for on Gusto MCP, scoped per user.

CALL ANY TOOL

List employees and departments, retrieve payroll details, check pay periods, and view pay schedules.

gustomcp_accept_reasonable_salary

Accept reasonable salary

Accept the most recently calculated reasonable-salary estimate (from calculate_reasonable_salary) for a Solo S-corp owner, recording it as their W-2 salary for IRS-defensibility. Call only after the user has reviewed and explicitly confirmed the estimate.

Parameters

Name

Type

Required

Description

_context

string

Optional

The original user question or request that prompted this tool call

gustomcp_calculate_reasonable_salary

Calculate reasonable salary

gustomcp_get_company

Get company

gustomcp_get_company_onboarding_package

Get company onboarding package

gustomcp_get_compensation

Get compensation

gustomcp_get_contractor_payment

Get contractor payment

gustomcp_get_contractor_payment_group

Get contractor payment group

gustomcp_get_employee

Get employee

gustomcp_get_employee_home_address

Get employee home address

gustomcp_get_employee_rehire

Get employee rehire

gustomcp_get_job

Get job

gustomcp_get_onboarding_answer

Get onboarding answer

gustomcp_get_pay_schedule

Get pay schedule

gustomcp_get_time_sheet

Get time sheet

gustomcp_list_contractor_payment_groups

List contractor payment groups

gustomcp_list_contractor_payments

List contractor payments

gustomcp_list_custom_fields_schema

List custom fields schema

gustomcp_list_earning_types

List earning types

gustomcp_list_employee_employment_history

List employee employment history

gustomcp_list_employee_jobs

List employee jobs

gustomcp_list_employee_work_addresses

List employee work addresses

gustomcp_list_job_compensations

List job compensations

gustomcp_list_pay_periods

List pay periods

gustomcp_list_pay_schedules

List pay schedules

gustomcp_list_payrolls

List payrolls

gustomcp_record_time

Record time

Record time for an employee or contractor (identified by company_member_uuid, from list_time_records), either adding a new shift or updating an existing one via on_existing. shift_started_at, shift_ended_at, and timezone are always required, but may be sent as null on an update to leave that field unchanged; updates additionally require shift_id.

Parameters

Name

Type

Required

Description

company_member_uuid

string

Required

The company member UUID for the worker whose time is being recorded, from list_time_records' companyMemberUuid field

company_uuid

string

Required

The company's UUID

shift_ended_at

string

Required

ISO8601 timestamp with explicit UTC offset for the end of the shift, in the past. Must be later than shift_started_at. Null leaves the stored end alone on an update; refused on an add

shift_started_at

string

Required

ISO8601 timestamp with explicit UTC offset for the start of the shift. Must be earlier than shift_ended_at. Null is only meaningful when on_existing is "update", where it leaves the stored start alone; refused on an add

timezone

string

Required

IANA timezone of the worker (e.g. America/Los_Angeles). Sets the tracker's timezone when one isn't already set. Null leaves the stored timezone alone on an update

_context

string

Optional

The original user question or request that prompted this tool call

hours_worked

number

Optional

Only used for external/third-party time tracking; ignored for native. Overrides the hours derived from the shift window rather than validating against it

job_uuid

string

Optional

The job UUID the hours belong to, from list_employee_jobs. Required on a native update; omit entirely for a contractor

note

string

Optional

Optional note to attach to the entry. Only used for native time tracking; dropped (with a warning) for third-party

on_existing

string

Optional

Whether to add a new entry alongside existing time, or update an existing one. Defaults to add when omitted. update also requires shift_id

ot_policy_approved

boolean

Optional

Only relevant for external/third-party time tracking with unclassified hours. Set true once the admin has explicitly approved the overtime policy suggestion returned by a prior refusal

shift_id

string

Optional

Required when on_existing is "update". For native time tracking it's a shift's id under shifts; for third-party it's the timesheet's own top-level id under timesheets

gustomcp_run_payroll

Run payroll

gustomcp_save_company_onboarding_answer

Save company onboarding answer

gustomcp_search_business_info

Search business info

gustomcp_update_payroll

Update payroll

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the user, and your hr agent can use Gusto MCP 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: ["gustomcp"], toolNames: ["gustomcp_list_employees", "gustomcp_get_employee", "gustomcp_list_pay_periods"] },
  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: ["gustomcp"], toolNames: ["gustomcp_list_employees", "gustomcp_get_employee", "gustomcp_list_pay_periods"] },
  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: ["gustomcp"], toolNames: ["gustomcp_list_employees", "gustomcp_get_employee", "gustomcp_list_pay_periods"] },
  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/gustomcp",
    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 Gusto MCP.

Employees & org

Copy the prompt

Copied

List all active employees in [department].

Copy the prompt

Copied

Get profile for [employee name].

Copy the prompt

Copied

How many employees are in [office location]?

Copy the prompt

Copied

Which employees were hired this month?

Payroll & schedules

Copy the prompt

Copied

What is the next pay period date?

Copy the prompt

Copied

List all pay schedules.

Copy the prompt

Copied

Get payroll summary for [pay period].

Copy the prompt

Copied

Which employees have pending status changes?

Reporting

Copy the prompt

Copied

Headcount by department.

Copy the prompt

Copied

New hires this quarter.

Copy the prompt

Copied

List employees with upcoming work anniversaries.

Copy the prompt

Copied

Which departments grew most this year?

SEE HOW AUTH WORKS

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

Authorize

Your user connects

Gusto MCP

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

Gusto MCP

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

Gusto MCP

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

Gusto MCP

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 hr agents and MCP connectors. Working code, live demos, fork what fits.

People Ops and HR teams

Offer letter routing agent

Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.

People Ops and HR teams

Performance review collector

Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

GTM and RevOps Teams

Revenue forecast commentary

Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

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.

Gusto MCP 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 Gusto MCP 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 Gusto OAuth token 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 Gusto MCP?

Yes. Pass a tool name filter to listScopedTools so the HR agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Gusto MCP.

What happens when a user revokes Gusto MCP 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 payroll data for all employees regardless of the user's HR role?

Only data the authorizing user's Gusto OAuth scope permits. Admin roles see full payroll; manager roles see their reports. Sensitive compensation data respects Gusto's native role-based access controls.

What other MCP connectors does Scalekit support?

Scalekit runs the QuickBooks MCP server, Dynamo Software MCP server, and HarvestAPI MCP server on the same per-user auth, token vault, and audit trail. Browse 500+ connectors in the MCP connector directory.