Harvest MCP connector for AI agents

CALL ANY TOOL

Run time tracking end to end: start timers, log hours, report billable time, watch project budgets, and invoice tracked work.

harvestmcp_list_time_entries

List time entries

List time entries, most recent first, defaulting to the last 30 days. Filter by project, user, date range, or invoiced status; paginate via cursor.

Parameters

Name

Type

Required

Description

from

string

Optional

Inclusive start date (YYYY-MM-DD).

to

string

Optional

Inclusive end date (YYYY-MM-DD).

project_id

integer

Optional

Filter to a single project. Omit for all projects.

user_id

integer

Optional

Filter to a single user. Omit to default to yourself.

is_invoiced

boolean

Optional

true for invoiced only, false for uninvoiced only. Omit for both.

harvestmcp_get_time_report

Get time report

harvestmcp_start_timer

Start timer

harvestmcp_log_time

Log time

harvestmcp_list_projects

List projects

harvestmcp_get_project_budget

Get project budget

harvestmcp_create_invoice_from_tracked_time

Invoice tracked time

harvestmcp_list_invoices

List invoices

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Harvest tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["harvestmcp"], toolNames: [
    "harvestmcp_list_time_entries",
    "harvestmcp_get_time_report",
    "harvestmcp_get_project_budget"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "How many billable hours did the team log this week?" }] });

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["harvestmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which projects are close to their budget?" }],
  tools,
});

// Execute the tool call with the user's vaulted Harvest credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["harvestmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Draft an invoice from Acme's uninvoiced June time." }],
  tools,
});

// Tool call runs with the user's vaulted Harvest credential
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["harvestmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "harvest_time_agent",
  model: "gemini-2.5-pro",
  instruction: "Track time and manage Harvest projects for the signed-in user.",
  tools,
});

await agent.run("Is the website redesign project over budget?");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Harvest tool. Click to copy, paste into your agent, done.

Track time

Copy the prompt

Copied

Start a timer on the Acme redesign, design task.

Copy the prompt

Copied

Log 1.5 hours to internal meetings for today.

Copy the prompt

Copied

Is a timer running right now? Stop it if so.

Copy the prompt

Copied

Submit my timesheet for this week.

Reports and budgets

Copy the prompt

Copied

How many billable hours did the team log this week?

Copy the prompt

Copied

Which projects have used more than 80 percent of their budget?

Copy the prompt

Copied

Show uninvoiced hours by client for June.

Invoices and clients

Copy the prompt

Copied

Draft an invoice from Acme's uninvoiced June time.

Copy the prompt

Copied

List open invoices due this month.

Copy the prompt

Copied

Which invoices are late, and for how much?

SEE HOW AUTH WORKS

Your users connect once. Their Harvest credentials stay vaulted, every call is scope-checked, and every action is logged.

1

Authorize

Your user connects

Harvest 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

2

Store

Their

Harvest 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

3

Resolve

When your agent calls a

Harvest 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

4

Audit

Every

Harvest 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

See the same per-user auth pattern across other productivity connectors.

OPS

Email-to-calendar scheduling agent

Parse scheduling intent from Gmail threads and create Google Calendar events with the right attendees and timezone.

Gmail

Google Calendar

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. Connectors follow.

01.

Shared tokens break per-user analytics

A shared Harvest token looks fine in a demo. In production every logged hour, timer, and invoice looks like one service account, and you cannot tell who tracked the time or drafted the bill. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Harvest today. Ten connectors 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 Harvest as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every timer, logged hour, and invoice in your audit trail is attributed to a real user, not a shared service account.

Where is the Harvest token stored?

In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.

Can I limit what the agent does in Harvest?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example time reports and budget reads without create_invoice or delete_time_entry. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

Can the agent delete time entries or send invoices on its own?

Only if you allow it. delete_time_entry is permanent in Harvest, so most teams exclude it via the toolNames filter, and invoices the agent creates land as drafts for a human to review and send. Every write is scope-checked and logged either way.

Harvest MCP

Tools your time agent reaches for on Harvest, scoped per user.