HarvestAPI

Live

OAUTH 2.0

TIME TRACKING

Accounting & Finance

Every time entry, project, and invoice your team logs lives in Harvest. HarvestAPI MCP gives your agent authenticated access to time and billing data scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the HarvestAPI account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
HarvestAPI
agent · Acme Q3
Run
How many billable hours did the engineering team log this week by project?
S
harvest_time_entries_list
75ms
Time tracking agent
142 billable hours this week. API platform: 48h (Sarah 18h, James 16h, Maria 14h), Mobile app: 36h, Infra: 31h, Client integrations: 27h.
Sources: engineering team, this week
harvestapimcp
142 hours
18:29
Message Claude...

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

CALL ANY TOOL
List and create time entries, manage projects and tasks, and pull invoice and billing data.
harvestapi_bulk_scrape_profiles
Bulk Scrape Profiles
Batch scrape multiple LinkedIn profiles in a single request using the HarvestAPI Apify scraper. Accepts a JSON array of LinkedIn profile URLs. Pricing: $4 per 1,000 profiles, $10 per 1,000 with email. Requires an Apify API token from https://console.apify.com/settings/integrations.
Parameters
Name
Type
Required
Description
apify_token
string
Required
Your Apify API token from https://console.apify.com/settings/integrations.
profile_urls
array
Required
JSON array of LinkedIn profile URLs to scrape in bulk.
find_email
boolean
Optional
When true, attempts email discovery for all profiles. Costs $10 per 1,000 instead of $4.
harvestapi_get_ad
Get Ad
harvestapi_get_comment_reactions
Get Comment Reactions
harvestapi_get_company
Get Company
harvestapi_get_company_posts
Get Company Posts
harvestapi_get_group
Get Group
harvestapi_get_post
Post get
harvestapi_get_post_comments
Get Post Comments
harvestapi_get_post_reactions
Get Post Reactions
harvestapi_get_profile_comments
Get Profile Comments
harvestapi_get_profile_posts
Get Profile Posts
harvestapi_get_profile_reactions
Get Profile Reactions
harvestapi_scrape_company
Scrape Company
harvestapi_scrape_job
Scrape Job
harvestapi_scrape_profile
Scrape Profile
harvestapi_search_ads
Search Ads
harvestapi_search_companies
Search Companies
harvestapi_search_geo
Search Geo
harvestapi_search_groups
Search Groups
harvestapi_search_jobs
Search Jobs
harvestapi_search_leads
Search Leads
harvestapi_search_people
Search People
harvestapi_search_posts
Search Posts
harvestapi_search_services
Search Services
Build your Agent
Drop the toolkit in, point it at the user, and your time tracking agent can use HarvestAPI from the first run.
Python · LlamaIndex
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: ["harvestapi"], toolNames: ["harvest_time_entries_list", "harvest_time_entry_create", "harvest_projects_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: ["harvestapi"], toolNames: ["harvest_time_entries_list", "harvest_time_entry_create", "harvest_projects_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: ["harvestapi"], toolNames: ["harvest_time_entries_list", "harvest_time_entry_create", "harvest_projects_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/harvestapi",
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 HarvestAPI.
Search & recall
Copy the prompt
Copied
List my time entries for this week.
Copy the prompt
Copied
How many hours did [person] log on [project] this month?
Copy the prompt
Copied
Show all time entries for [project] today.
Copy the prompt
Copied
Which projects have exceeded budget this quarter?
Action & logging
Copy the prompt
Copied
Log 2 hours on [project] today: [notes].
Copy the prompt
Copied
Create a time entry for [task] on [date].
Copy the prompt
Copied
Update notes on time entry [id].
Copy the prompt
Copied
Delete time entry [id].
Invoices & billing
Copy the prompt
Copied
List all open invoices.
Copy the prompt
Copied
Which invoices are overdue?
Copy the prompt
Copied
Get billing summary for [client] this month.
Copy the prompt
Copied
Total billable hours by client this quarter.
SEE HOW AUTH WORKS
Users authorize HarvestAPI once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
HarvestAPI
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
HarvestAPI
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
HarvestAPI
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
HarvestAPI
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 time tracking agents and MCP connectors. Working code, live demos, fork what fits.
ENGINEERING
Engineering standup agent
Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.
ENGINEERING
DevOps assistant agent
Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.
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.
HarvestAPI 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 HarvestAPI 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 HarvestAPI 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 HarvestAPI?
Yes. Pass a tool name filter to listScopedTools so the time tracking agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches HarvestAPI.
What happens when a user revokes HarvestAPI 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 log time on behalf of other team members?
Only if the authorizing user has admin rights in Harvest. Regular user tokens log time for that user only. Admin tokens can log for others if account-level settings permit cross-user time entry.
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"": {
""harvestapi"": {
""url"": ""https://mcp.scalekit.com/harvestapi"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.harvestapi]
url = ""https://mcp.scalekit.com/harvestapi""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""harvestapi"": {
""url"": ""https://mcp.scalekit.com/harvestapi"",
""type"": ""http""
}
}
}