Tableau MCP | OAuth 2.0 Tableau connector for AI agents

CALL ANY TOOL

List workbooks and dashboards, download view data as CSV, browse published data sources, and monitor refresh jobs.

tableau_workbooks_list

List workbooks

List Tableau workbooks the user can access.

Parameters

Name

Type

Required

Description

site_id

string

Optional

Tableau site ID filter

limit

integer

Optional

Max workbooks

tableau_views_list

List views

tableau_view_data

Download view data

tableau_datasources_list

List data sources

tableau_jobs_list

List refresh jobs

Build your Agent

Drop the toolkit in, point it at the user, and your bi agent can use Tableau from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tableau"], toolNames: ["tableau_workbooks_list", "tableau_views_list", "tableau_view_data"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tableau"], toolNames: ["tableau_workbooks_list", "tableau_views_list", "tableau_view_data"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tableau"], toolNames: ["tableau_workbooks_list", "tableau_views_list", "tableau_view_data"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/tableau",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Tableau.

Workbooks & views

Copy the prompt

Copied

List all workbooks I have access to.

Copy the prompt

Copied

List views in [workbook name].

Copy the prompt

Copied

Pull data from [dashboard name].

Copy the prompt

Copied

Which workbooks were updated this week?

Data & refreshes

Copy the prompt

Copied

List all published data sources.

Copy the prompt

Copied

Which extract refreshes failed today?

Copy the prompt

Copied

Get data behind [view name] as CSV.

Copy the prompt

Copied

Which refresh jobs are running right now?

Reporting

Copy the prompt

Copied

Pull executive revenue dashboard data for Q3.

Copy the prompt

Copied

Which dashboards have the most views this month?

Copy the prompt

Copied

Get data from [sheet] in [workbook].

Copy the prompt

Copied

List all workbooks with failed refreshes.

SEE HOW AUTH WORKS

Users authorize Tableau once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Tableau

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Tableau

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Tableau

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Tableau

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other bi agents and MCP connectors. Working code, live demos, fork what fits.

GTM

Salesforce customer insights agent

Surface Salesforce account activity, NPS signals, and renewal flags into Slack threads for the account team.

Salesforce

Slack

View agent

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Tableau today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Tableau as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Tableau oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Tableau?

Yes. Pass a tool name filter to listScopedTools so the BI agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Tableau.

What happens when a user revokes Tableau access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent access workbooks published by other users with restricted permissions?

Only workbooks the authorizing user has view access to in Tableau Server/Cloud. Row-level security rules on embedded data sources apply. Restricted workbooks are blocked at the Tableau permission layer.

Tableau

Tools your bi agent reaches for on Tableau, scoped per user.