Tableau for AI agents
Tableau is a visual analytics platform where dashboards, workbooks, and data sources live, and analysts here pull that reporting information into other workflows without opening the app. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Tableau.
List workbooks in a project
Pull the list of workbooks in a project so an agent can find the right dashboard to reference.
Look up a workbook's details
Read a specific workbook's metadata before summarizing it, a lookup that changes nothing on the server.
Check a data refresh job's status
Check the status of a running extract job to know when the underlying data was last refreshed.
10 Tableau actions, graded by risk.
Every Tableau action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
10Look things up. Allowed by default.
- tableau.list_jobsList Jobs
- tableau.list_usersList Users
- tableau.list_viewsList Views
- tableau.list_groupsList Groups
- tableau.get_workbookGet Workbook
- tableau.list_projectsList Projects
- tableau.list_workbooksList Workbooks
- tableau.get_server_infoGet Server Info
- tableau.list_data_sourcesList Data Sources
- tableau.get_current_sessionGet Current Session
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Tableau in three steps.
- 01Your users connect TableauThey add their Tableau api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Tableau through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('tableau', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Tableau connects.
Users add their Tableau api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Tableau connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Tableau from any agent.
Tableau and Arc0, answered.
Can I use Tableau with Claude, ChatGPT or Cursor?
Yes. Connect Tableau to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Tableau actions you allow.
How do users connect Tableau?
Users add their Tableau api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Tableau actions can my agent take?
10 in total: 10 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Tableau?
Yes. Allow read actions and deny writes in the Tableau policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Tableau too?
Yes. The same Tableau connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Tableau into your agent.
Your users connect Tableau once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan