Connect Claude to Tableau

Search and browse Tableau workbooks, views and data sources, read a view's data, and query a published data source. Toolspoke puts 12 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Sandboxed MCP server
Authentication: Personal access token
Actions exposed: 12
What a call bills: Sandbox time only
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Tableau
Open the marketplace in your workspace, add Tableau to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with personal access token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Tableau shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Tableau asks for

Personal access token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Server URLRequired: The address before /#/ when you open Tableau in a browser - your Tableau Cloud pod, e.g. https://prod-useast-a.online.tableau.com, or your Tableau Server's address.; https://prod-useast-a.online.tableau.com
SiteOptional: The site's content URL - the part after /site/ in the browser address. Leave blank for the Default site on Tableau Server.; acme
Personal access token nameRequired: Tableau → your avatar → My Account Settings → Personal Access Tokens → Create Token. Enter the token's name exactly as created; it is case-sensitive.; toolspoke
Personal access token secretRequired: The secret shown once when the token is created. The token acts with your own site role and permissions. Create one just for this connector - Tableau ends a token's earlier session when it signs in again, so sharing a token with another tool signs one of them out.; AbCdEf…==:GhIjKl…

What Claude can do in Tableau

12 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 12Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

search_content
Search the site's content - workbooks, views, data sources, projects, flows, tables - by terms, optionally narrowed by type, owner or modified time and ordered by usage. Start here when you do not already have an id.
list_projects
List the site's projects, the folders content is published into.
list_workbooks
List workbooks on the site with their project, owner and update time. It is also the install's connection test, because it signs in and reads real content.
get_workbook
Read one workbook with its views.
list_views
List views (sheets and dashboards) on the site, with the workbook each belongs to.
get_view
Read one view's metadata.
get_view_data
Read the data behind one view as CSV, optionally with view filters applied. Not written to the audit log, because it is the site's data.
list_datasources
List published data sources on the site. The datasource LUID is what get_datasource_metadata and query_datasource take.
get_datasource_metadata
Read a published data source's fields - names, types, roles and descriptions. Call this before query_datasource; field captions must match exactly.
query_datasource
Query a published data source through VizQL Data Service. Name the fields by fieldCaption, with a function such as SUM for measures, and add filters if needed. Not written to the audit log, because it returns the site's data.
list_jobs
List background jobs such as extract refreshes and flow runs, with their status. Needs a site administrator's token.
list_users
List the site's users with their site role. Needs a site administrator's token.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 12 actions above are the whole of it. A call to any other name is refused before it reaches Tableau rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It only reads: Every action here reads. Nothing this connector can do changes anything in Tableau.
It reaches no further than your credential: Toolspoke holds no access to Tableau of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Tableau: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Tableau. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Tableau's own rate limits. A call that Tableau refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Tableau?

12 named actions: 12 that only read. They include search_content, list_projects and list_workbooks. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Tableau connector need?

Personal access token. The connector asks for server url, personal access token name and personal access token secret, and optionally site. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Tableau connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 12 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Tableau connector not do?

The 12 actions above are the whole of it. A call to any other name is refused before it reaches Tableau rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in Tableau. Toolspoke holds no access to Tableau of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Tableau. An agent has to ask. Toolspoke does not retry, queue or back off around Tableau's own rate limits. A call that Tableau refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Tableau's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Tableau?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More analytics connectors

Browse all of them