Tableau

Tableau

Tableau Cloud and Server: find workbooks, views and data sources, read view data as CSV, images and PDFs, query published data sources, trace lineage, manage projects, tags, group members and extract refreshes.

7 天免费 · 无需信用卡 · EU 托管

问 Tableau 任何事

通过 AnythingMCP 对 Tableau 试一个真实提示 — Claude 调用工具并返回答案。在你的消息上按 Enter 即可在 Cloud 安装。

在 Cloud 上安装 Tableau
Tableau · 通过 MCP 实时
分享
Opus 4.7

Claude 是 AI,可能会出错。请核对回答。

2 分钟设置

  1. 1在 cloud.anythingmcp.com 开始免费试用。
  2. 2在连接器商店点击 Tableau。提示时粘贴凭据。
  3. 3生成 MCP API 密钥,将 AI 客户端指向生成的 MCP URL。
立即安装 Tableau

Tableau 指南

面向主流 AI 客户端的逐步设置。

配置 Tableau

直接来自连接器定义:在哪里获取凭据、需要哪些权限,以及该适配器调用的是哪个 API。 由连接器作者以英文提供。

Tableau

This connector works with Tableau Cloud and Tableau Server (2024.2 or later) through the REST API 3.23, the VizQL Data Service and the Metadata API: sites, projects, workbooks, views (data as CSV, images, PDFs, Excel crosstabs), published data sources and their fields, queries on data sources, lineage, users and groups, background jobs and extract refreshes.

Setup (5 minutes)

  1. In Tableau open your Account Settings, section Personal Access Tokens, enter a token name and click Create Token. Copy the name into TABLEAU_PAT_NAME and the secret (shown once) into TABLEAU_PAT_SECRET. On Tableau Server an admin may have to allow personal access tokens first.
  2. TABLEAU_SERVER_URL: the address without a path, e.g. https://prod-useast-a.online.tableau.com (Tableau Cloud: the pod host you see in the browser) or https://tableau.example.com.
  3. TABLEAU_SITE: the site's content URL, the part after /site/ in the browser address (#/site/acme/home gives acme). For the Default site of a Tableau Server leave it empty.
  4. Run tableau_get_current_session to check the sign-in.

The connector signs in with the token and reuses the session; it signs in again when the session expires. Tableau allows one session per token at a time, so do not use the same token in another tool, and Tableau Cloud revokes a token that has not been used for 15 days (create a new one then).

Workflow

  • Start with tableau_get_current_session: site.id is the site_id every site tool needs. tableau_get_server_info, tableau_list_sites and tableau_get_site describe the server and site.
  • Find content: tableau_search_content (words, with type filters), tableau_list_projects, tableau_list_workbooks, tableau_get_workbook, tableau_list_workbook_views, tableau_list_views, tableau_get_view, tableau_list_workbook_connections.
  • Read what a dashboard shows: tableau_get_view_data (CSV of the marks), tableau_get_view_image (PNG to look at), tableau_get_view_pdf, tableau_download_view_crosstab_excel, tableau_get_workbook_pdf. Narrow them with filters such as {"vf_Region": "West"}.
  • Query data directly: tableau_list_datasources, tableau_get_datasource, tableau_list_datasource_connections, then tableau_read_datasource_metadata for the field captions and tableau_query_datasource to aggregate and filter them (VizQL Data Service).
  • Lineage and impact: tableau_metadata_query (GraphQL on the Metadata API, for example which workbooks use a table).
  • People: tableau_list_users, tableau_get_user, tableau_list_user_groups, tableau_list_groups, tableau_list_group_users, tableau_add_user_to_group.
  • Refreshes and jobs: tableau_list_extract_refresh_tasks, tableau_run_extract_refresh_task, tableau_refresh_workbook, tableau_refresh_datasource, then tableau_list_jobs and tableau_get_job to follow them; tableau_cancel_job stops one.
  • Organize: tableau_create_project, tableau_update_project, tableau_update_workbook, tableau_move_workbook, tableau_add_workbook_tags, tableau_add_datasource_tags.

Switched off at install: tableau_cancel_job; it cannot be undone, so an admin switches it on when the team needs it.

Reading the answers: ids are LUIDs (UUIDs). Lists come as {"pagination": {"pageNumber", "pageSize", "totalAvailable"}, "workbooks": {"workbook": [...]}} (the same for projects, views, datasources, users, groups, jobs). Times are ISO 8601 in UTC. tableau_get_view_data returns CSV text with a header row; numbers are formatted as in the view. tableau_query_datasource returns data as a list of objects keyed by field caption (with the function, e.g. SUM(Sales)). A job's finishCode is 0 for success, 1 for failure, 2 for cancelled.

Paging: list tools take page_size (up to 1000) and page_number; continue while pageNumber * pageSize is below totalAvailable. tableau_search_content pages with limit and page; its answer carries the total and the next page.

Filters and sorting: filter is field:operator:value, several joined by commas, e.g. projectName:eq:Finance,updatedAt:gt:2026-01-01T00:00:00Z; in takes [a,b]. sort is field:asc or field:desc.

Limits and requirements: tableau_read_datasource_metadata and tableau_query_datasource need Tableau Cloud or Tableau Server 2025.1 with the VizQL Data Service on, and the API Access capability on the data source. tableau_metadata_query needs the Metadata API (on by default on Tableau Cloud; enabled by an admin on Server). tableau_search_content needs Tableau Cloud or Server 2022.3 and later. Content Tableau returns is limited to what the token's user may see.

Errors: Tableau answers {"error": {"code", "summary", "detail"}}. 401 (codes 401001 and 401002) means a wrong or expired token or wrong site content URL; 403 a user without permission; 404 (404000 to 404xxx) a wrong id or a site_id from another site; 400 a bad filter or parameter; 409 a duplicate name or a refresh that is already queued.

你的 AI 距离 Tableau 仅两次点击。

安装连接器、粘贴凭据、向 AI 提问。7 天免费,无需信用卡。