agentmods.dev

auth

auth is a cursor rule for Cursor from YoshitakaArakawa/tableau-mcp-apps-lab. It costs 0 tokens per session (878 once invoked), scanned A, a copy of auth, Apache-2.0.

Authentication rules for the Tableau MCP server, covering passthrough authentication and two OAuth flows. OAuth is a standard way for an application to obtain permission to access another service without handling the user's password.

In plain words
What is it for?
Use them when changing Tableau authentication, OAuth providers, access-token validation, middleware, sessions, or security-related error handling.
Why use it?
They define how requests are checked, how authentication middleware is ordered, and how tokens and sessions must be handled securely.

Cursor rule for Cursor

not rated 0 1mo ago A scan 0 tokens copy · 100% Apache-2.0
View the source file YoshitakaArakawa/tableau-mcp-apps-lab
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.

agentmods
npx agentmods add rules/yoshitakaarakawa/tableau-mcp-apps-lab/auth
Clone the repo
git clone --depth 1 https://github.com/YoshitakaArakawa/tableau-mcp-apps-lab

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.

agentmods badge for auth

README.md
[![agentmods](https://agentmods.dev/badge/rules/yoshitakaarakawa/tableau-mcp-apps-lab/auth.svg)](https://agentmods.dev/rules/yoshitakaarakawa/tableau-mcp-apps-lab/auth)
Your own site
<a href="https://agentmods.dev/rules/yoshitakaarakawa/tableau-mcp-apps-lab/auth"><img src="https://agentmods.dev/badge/rules/yoshitakaarakawa/tableau-mcp-apps-lab/auth.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 878 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00878
Opus 5 $0.00000 $0.00439
Sonnet 5 $0.00000 $0.00176
Haiku 4.5 $0.00000 $0.00088

Measured 4d ago against content hash 8d49ceb6fc28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

auth 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 4d 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 auth — 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/auth.mdc · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auth Standards

Three Auth Paths

1. Passthrough Auth

  • Header x-tableau-auth or cookie workgroup_session_id
  • Validated via RestApi.authenticatedServerMethods.getCurrentServerSession()
  • Optional session caching via ExpiringMap (configurable interval)
  • Location: src/server/passthroughAuthMiddleware.ts
  • Enabled when config.enablePassthroughAuth is true
  • MCP scopes NOT enforced (no way to verify original token scopes)

2. Embedded OAuth (PKCE)

  • JWE-encrypted MCP access tokens signed with server's private key
  • Contains embedded Tableau access/refresh tokens
  • EmbeddedAccessTokenValidator validates via jose
  • Location: src/server/oauth/provider.ts, accessTokenValidator.ts, token.ts, authorize.ts, callback.ts

3. Tableau Cloud OAuth

  • Tableau Cloud JWT Bearer tokens
  • TableauAccessTokenValidator validates JWT claims
  • Location: src/server/oauth/provider.ts, accessTokenValidator.ts

Middleware Chain Order (express.ts)

handlePingRequest
  → passthroughAuthMiddleware (if enabled)
    → oauthProvider.authMiddleware
      → validateProtocolVersion
        → createMcpServer

Auth Info Flow

req.auth
  → getTableauAuthInfo(req.auth)
    → TableauAuthInfo (discriminated union: 'X-Tableau-Auth' | 'Bearer' | 'Passthrough')
      → TableauRequestHandlerExtra.tableauAuthInfo
        → useRestApi() (handles sign-in, token setup, sign-out lifecycle)

TableauAuthInfo Type (src/server/oauth/schemas.ts)

Discriminated union on type field:

  • 'X-Tableau-Auth' — username, server, siteId?, userId?, accessToken?, refreshToken?
  • 'Bearer' — username, server, siteId, userId?, raw (the JWT string)
  • 'Passthrough' — username, userId, server, siteId, raw (the session token)

REST API Auth Lifecycle (src/restApiInstance.ts)

useRestApi() is the single entry point for all authenticated API calls:

  • Creates a fresh RestApi instance per call
  • Routes to correct auth method based on tableauAuthInfo.type and config.auth
  • Auth methods: pat, direct-trust, uat, oauth
  • PAT/direct-trust sessions are ephemeral (signed out after use)
  • OAuth/passthrough sessions are long-lived (NOT signed out)
  • Accepts jwtScopes for direct-trust/UAT token generation

Read the full file on GitHub · 87 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.

  1. 4d ago First seen · 87 lines · 0 tokens per session scan A 8d49ceb6fc28

Subscribe to this mod's changes

auth is a cursor rule published in the GitHub repository YoshitakaArakawa/tableau-mcp-apps-lab (0 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 878 tokens. A static security scan graded it A with 0 findings. It is 100% identical to auth, differing in 0 lines, and is treated as a copy.

Security
Related

Other cursor rules, from other repositories

ponytail

Ponytail, lazy senior dev mode. Always pick the simplest solution that works.

DietrichGebert/ponytail · 576 tokens

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens

dev-standard

Apache Superset development standards and guidelines for Cursor IDE.

apache/superset · 1,147 tokens

cli-error-handling

CLI command error handling patterns.

prisma/orm · 0 tokens

prefer-direct-imports-over-module-mocks

Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.

prisma/orm · 0 tokens

control-plane-descriptors

Control plane descriptor and instance implementation patterns.

prisma/orm · 0 tokens