Harvest + Claude Code

Build a Harvest reader with Claude Code Prepare a grounded recorded-hours briefing

Use Claude Code to build a separate read-only Harvest assistant with Agent200. Ground the recorded-hours briefing in returned source data.

On this page
  1. Overview
  2. Before you start
  3. Setup steps
  4. Test your connection
  5. Instructions for AI agents
  6. Harvest tools
  7. How it works
  8. Troubleshooting
  9. FAQ

Overview

Use Claude Code to implement a read-only Harvest reader in your application. Validate identifiers, schemas and access failures before presenting a recorded-hours briefing.

Start with one identified time entry. Preserve returned entry dates, hours, project and task IDs, and report totals actually returned; report missing data and keep the workflow read-only.

Provider reference: Harvest API.

Connector
Harvest
Works with
Claude Code · Coding agent, with the SDK
Authentication
Managed OAuth, per end user
Tools
6 tools
Model in examples
openai/gpt-5.6-sol

Before you start

  • An Agent200 API key. Create one on the API keys page of the dashboard.
  • Harvest enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
  • An end user with a Harvest account. They approve access once, on Harvest's own page.
  • Claude Code in your project. It writes the code with the Agent200 SDK; you review it.

Connect Harvest to Claude Code

  1. 1

    Step 1: Create your Agent200 API key

    Create a key on the API keys page and store it securely.

    .env
    Conceptual example
    Store the Agent200 API key as an environment variable
    # Keep the key out of your code, prompts and chats.
    export AGENT200_API_KEY="paste-your-key-here"
  2. 2

    Step 2: Inspect the real tool definitions

    Confirm the actual Harvest read operations and input schemas in your runtime.

  3. 3

    Step 3: Connect the user’s Harvest account

    Preserve the same stable user identity during authorization and later requests.

    connect.js
    Conceptual example
    Let an end user connect their account (managed OAuth)
    // Each end user authorizes their own Harvest account, once.
    const connection = await agent200
      .user("user_123")
      .connect("harvest");
    
    if (connection.authorizationUrl) {
      // Show this link to your user; Agent200 handles the rest.
      console.log(connection.authorizationUrl);
    }
  4. 4

    Step 4: Build and test the read-only answer

    Prepare the recorded-hours briefing only from returned source data. The code example illustrates a sequence, not an SDK installation contract.

    run.js
    Conceptual example
    Run a request with the connector's tools
    const result = await agent200
      .user("user_123")
      .run({
        model: "openai/gpt-5.6-sol",
        input: "How many hours did we log on the website project this month",
        tools: ["harvest"],
      });
    
    console.log(result.output);

Test your connection

Run one request to check everything is wired up.

Ask

Review my Harvest time entries for the date range I provide. Use only the selected account and accessible records. Report hours by returned project and task, with any access gaps; do not change entries.

What should come back

  • The selected time entry is identified.
  • Only returned entry dates, hours, project and task IDs, and report totals actually returned are reported.
  • Access gaps and missing context are explicit; no source data is changed.

Check the selected Harvest account, connected role, date range, project permission and pagination. A 403 or empty page does not prove the organization has no time entries.

Get your API key

Create a key in the Agent200 dashboard. It reaches Harvest and every other connector enabled for your project.

Read the SDK docs

Instructions for AI agents

Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Harvest to Claude Code.

Agent brief
Goal: connect Harvest to Claude Code with Agent200.
Guide: https://www.agent200.com/connectors/harvest/framework/claude-code/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Make sure Harvest is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's Harvest account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Harvest.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "harvest" in the tools. The model decides when a Harvest tool is needed; Agent200 executes the call.
7. Check it works with this request: "Review my Harvest time entries for the date range I provide. Use only the selected account and accessible records. Report hours by returned project and task, with any access gaps; do not change entries."
   What should come back:
   - The selected time entry is identified.
   - Only returned entry dates, hours, project and task IDs, and report totals actually returned are reported.
   - Access gaps and missing context are explicit; no source data is changed.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Harvest, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

The whole guide is also available as Markdown, for agents and LLMs: /connectors/harvest/framework/claude-code.md

Harvest tools Claude Code can call

  • List time entries

    Read
    harvest_list_time_entries

    Find time entries within an explicit date, user or project scope.

  • Read a time entry

    Read
    harvest_get_time_entry

    Retrieve one identified time entry and its recorded details.

  • List projects

    Read
    harvest_list_projects

    Find projects when the connected role has project-list access.

  • Read a project

    Read
    harvest_get_project

    Retrieve one identified project when the connected role permits it.

  • Project time report

    Read
    harvest_time_report_by_project

    Read recorded time grouped by project for an explicit date range.

  • Task time report

    Read
    harvest_time_report_by_task

    Read recorded time grouped by task for an explicit date range.

How it works

  1. 01

    Your app sends the request

    It calls Agent200 with the model, instructions, the input, the end user's id and the Harvest tools.

  2. 02

    The model picks a tool

    The model decides whether a Harvest tool is needed, and with which arguments.

  3. 03

    Agent200 runs the call

    It uses that user's own Harvest connection, within the endpoints and scopes your project allows, and returns the result to the model.

  4. 04

    Your app gets the result

    Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's Harvest account.

Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and Harvest enforces what its API grants.

Troubleshooting

The source cannot be read

Check the selected Harvest account, connected role, date range, project permission and pagination. A 403 or empty page does not prove the organization has no time entries.

FAQ

How do I verify this result?

Compare the named time entry and returned entry dates, hours, project and task IDs, and report totals actually returned with the source. Treat missing information as missing, not as a fact.

Is this a native product integration?

This describes a separate application built with Agent200 and Claude Code; it does not install a connector into the Claude Code app.

Use Harvest with another framework

200 OK

Harvest, connected to Claude Code.
One SDK. One API key.

Agent200 handles the OAuth, the tokens and every tool call. You keep your agent, your model and your code.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)