Harvest MCP by usefulapi

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

• 连接方式: 在云端运行
• 传输方式: Streamable HTTP
• 分类: 其他

安装

选择你使用的 AI 应用，然后复制设置。

你需要

• 在云端运行无需安装任何东西，通过互联网连接

你用的是哪个应用？

https://harvest.usefulapi.io/mcp

claude mcp add --transport http harvest https://harvest.usefulapi.io/mcp

{
  "mcpServers": {
    "harvest": {
      "url": "https://harvest.usefulapi.io/mcp"
    }
  }
}

{
  "servers": {
    "harvest": {
      "type": "http",
      "url": "https://harvest.usefulapi.io/mcp"
    }
  }
}

https://harvest.usefulapi.io/mcp

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

• harvest_list_time_entries

  List time entries, optionally filtered by user, project, client, task, date range, running/billed status, or updated-since. Paginated. Harvest REST: GET /time_entries.

• harvest_get_time_entry

  Retrieve a single time entry by id. Harvest REST: GET /time_entries/{id}.

• harvest_list_projects

  List projects, optionally filtered by active status or client, or updated-since. Paginated. Harvest REST: GET /projects.

• harvest_get_project

  Retrieve a single project by id. Harvest REST: GET /projects/{id}.

• harvest_list_clients

  List clients, optionally filtered by active status or updated-since. Paginated. Harvest REST: GET /clients.

• harvest_get_client

  Retrieve a single client by id. Harvest REST: GET /clients/{id}.

• harvest_list_tasks

  List tasks (the billable/non-billable work categories that can be assigned to projects), optionally filtered by active status or updated-since. Paginated. Harvest REST: GET /tasks.

• harvest_list_users

  List users in the account, optionally filtered by active status or updated-since. Paginated. Harvest REST: GET /users.

• harvest_get_current_user

  Retrieve the currently authenticated user (whom the access token belongs to). Harvest REST: GET /users/me.

• harvest_list_project_assignments

  List the authenticated user's active project assignments — the projects and their assignable tasks the current user can log time against (use this to find the project_id + task_id for harvest_create_time_entry). Paginated. Harvest REST: GET /users/me/project_assignments.

• harvest_list_invoices

  List invoices, optionally filtered by client, project, state, date range, or updated-since. Paginated. Harvest REST: GET /invoices.

• harvest_get_invoice

  Retrieve a single invoice by id, including its line items. Harvest REST: GET /invoices/{id}.

• harvest_list_estimates

  List estimates, optionally filtered by client, state, date range, or updated-since. Paginated. Harvest REST: GET /estimates.

• harvest_list_expenses

  List expenses, optionally filtered by user, client, project, date range, billed status, or updated-since. Paginated. Harvest REST: GET /expenses.

• harvest_get_company

  Retrieve the company/account settings for the authenticated account (name, currency, time/date formats, week start, feature flags). Harvest REST: GET /company.

• harvest_create_time_entry

  Create a time entry. Requires project_id, task_id and spent_date. Provide `hours` to log a specific duration; OR provide `started_time` (+ optional `ended_time`) for a timestamped entry; OR omit both to start a running timer (on a timestamp-tracking account). Use harvest_list_pro

• harvest_update_time_entry

  Update an existing time entry's hours, notes, spent date, or project/task. Only the fields you provide are changed. Harvest REST: PATCH /time_entries/{id}. WRITE — modifies data.

• harvest_stop_time_entry

  Stop a currently running time entry (no-op error if it is already stopped). Harvest REST: PATCH /time_entries/{id}/stop. WRITE — modifies data.

• harvest_restart_time_entry

  Restart a previously stopped time entry, resuming its timer (error if it is already running). Harvest REST: PATCH /time_entries/{id}/restart. WRITE — modifies data.

• harvest_delete_time_entry

  Permanently delete a time entry by id. This cannot be undone. Harvest REST: DELETE /time_entries/{id}. WRITE — destroys data.

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

• ✓ 通过

  作者与仓库一致

  注册名称已通过域名 usefulapi.io 验证（注册中心会核实域名所有权）

• … 尚未检查

  仍在维护

  我们还没有从 GitHub 读取这个仓库

• … 尚未检查

  有许可证

  我们还没有从 GitHub 读取这个仓库

• ✓ 通过

  端点有响应

  在 13 毫秒内响应（HTTP 200）

• – 不适用

  使用 OAuth 登录

  无需登录

• ✓ 通过

  工具描述中没有隐藏指令

  已读取 20 个工具描述，未发现针对 AI 的隐藏指令

与“其他”中的其他服务器比较i

• 星标数多于此分类中其他 32451 个服务器的 0%
• 发布到注册中心的时间比此分类中其他 32451 个服务器的 96% 更新
• 基础检查结果等于或优于此分类中其他 32451 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

作者的 README

{