Project guidance for an official Tableau MCP server, which lets AI applications connect to Tableau Cloud and Tableau Server. Tableau is a platform for working with data, and MCP is a way for AI tools to call connected services.

Use it when working on the server layout, Tableau REST, metadata, data-source, or Pulse API connections, authentication, error handling, and tool registration.

It gives developers shared architecture and security rules for building and changing the server, especially its authentication code.

tableau-mcp — Cursor rule for Cursor by marcushojww

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/marcushojww/tableau-mcp-v2

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/rules/marcushojww/tableau-mcp-v2/tableau-mcp/github.svg)](https://agentmods.dev/rules/marcushojww/tableau-mcp-v2/tableau-mcp)

Your own site

<a href="https://agentmods.dev/rules/marcushojww/tableau-mcp-v2/tableau-mcp"><img src="https://agentmods.dev/badge/rules/marcushojww/tableau-mcp-v2/tableau-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/marcushojww/tableau-mcp-v2/tableau-mcp"><img src="https://agentmods.dev/badge/rules/marcushojww/tableau-mcp-v2/tableau-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 835 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00835
Opus 5	$0.00000	$0.00417
Sonnet 5	$0.00000	$0.00167
Haiku 4.5	$0.00000	$0.00084

Measured 8d ago against content hash cc303e1313e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tableau-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to tableau-mcp — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/tableau-mcp.mdc · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tableau MCP — Project Context

What This Is

Official Tableau MCP server (tableau/tableau-mcp). Provides MCP tools for AI applications integrating with Tableau Cloud and Server via REST API, VDS API, Metadata API, and Pulse API.

Role Context

Auth lead on this project. All auth-related code requires architectural rigor — not just working code.

Core Principles

Deterministic control over prompt hope for all auth paths
Programmatic enforcement for security-critical operations
Structured errors always — never silent failures
Understand before building — plan before coding

Architecture Overview

Source Layout

src/
├── config.ts              # Config loading from env
├── server.ts              # MCP Server class
├── restApiInstance.ts      # REST API lifecycle, auth, useRestApi()
├── index.ts               # Entry point (stdio/http)
├── tools/                 # MCP tools (factory pattern)
│   ├── tool.ts            # Base Tool class
│   ├── tools.ts           # Tool factory registry
│   ├── toolContext.ts     # TableauRequestHandlerExtra type
│   └── toolName.ts        # Tool name constants + groups
├── server/                # HTTP server & auth middleware
│   ├── express.ts         # Express setup, middleware chain
│   ├── passthroughAuthMiddleware.ts
│   └── oauth/             # OAuth provider, tokens, scopes
├── sdks/tableau/          # Tableau REST API client (Zodios)
├── utils/                 # Shared utilities
├── telemetry/             # Telemetry
└── logging/               # Structured logging

Key Libraries

ts-results-es — Result<T, E>, Ok(), Err() for tool callbacks
zod — Schema validation for params, auth tokens, configs
@zodios/core — Type-safe REST API client for Tableau APIs
jose — JWT/JWE operations for OAuth tokens
vitest — Test framework (NOT jest)

Tool Registry (All 16 Tools)

Datasource: list-datasources, get-datasource-metadata, query-datasource Workbook: list-workbooks, get-workbook View: list-views, get-view-data, get-view-image Pulse: list-all-pulse-metric-definitions, list-pulse-metric-definitions-from-definition-ids, list-pulse-metrics-from-metric-definition-id, list-pulse-metrics-from-metric-ids, list-pulse-metric-subscriptions, generate-pulse-metric-value-insight-bundle, generate-pulse-insight-brief Content Exploration: search-content

Read the full file on GitHub · 91 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 91 lines · 0 tokens per session scan A cc303e1313e4

Subscribe to this mod's changes

tableau-mcp is a cursor rule published in the GitHub repository marcushojww/tableau-mcp-v2 (0 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 835 tokens. A static security scan graded it A with 0 findings. It is 100% identical to tableau-mcp, differing in 0 lines, and is treated as a copy.

Building agents

tableau-mcp

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

Tableau MCP — Project Context

What This Is

Role Context

Core Principles

Architecture Overview

Source Layout

Key Libraries

Tool Registry (All 16 Tools)

What this file has done since we first saw it

Other cursor rules, from other repositories

ponytail

angular-20

dev-standard

cli-error-handling

prefer-direct-imports-over-module-mocks

control-plane-descriptors