agentmods.dev

tableau-mcp AGENTS.md

A set of project instructions for working on tableau-mcp, a server that lets coding agents access Tableau data tools. It describes the repository, its architecture, commands, and the expected implementation rules.

In plain words
What is it for?
Use it when implementing or reviewing features in the tableau-mcp repository, especially Tableau Desktop authoring tools.
Why use it?
It gives an agent the project context and the repository’s definition of correct work before code changes are made. It also documents how web and Tableau Desktop versions are built.

Instructions file for CodexOpenCode

329 3d ago A scan 1,883 tokens original Apache-2.0
View the source file tableau/tableau-mcp
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 instructions/tableau/tableau-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/tableau/tableau-mcp

Made for: Codex, OpenCode.

Per session 1,883 This file is loaded in full into every session.
When invoked 1,883 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.01883 $0.01883
Opus 5 $0.00941 $0.00941
Sonnet 5 $0.00377 $0.00377
Haiku 4.5 $0.00188 $0.00188

Measured 2d ago against content hash 46c55237cdc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tableau-mcp AGENTS.md 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 2d 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

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Repo-level contract for the global agent OS. Defines what "correct" means in tableau-mcp. Source of truth for agents before any implementation.

Staged copy. Target path on apply: repo root AGENTS.md (branch feature/authoring, or main). Encodes the canonical Desktop-tool migration pattern verified from merged PRs #347 (session) and #370 (workbook).

Project overview

@tableau/mcp-server — an MCP server "helping agents see and understand data." Exposes Tableau capabilities to MCP clients over stdio and HTTP. Ships multiple build variants (default web, desktop, combined) from one codebase via src/scripts/build.ts + esbuild conditional bundling. An active migration on feature/authoring ports Tableau Desktop authoring tools from the agent-to-tableau-desktop repo into src/tools/desktop/.

Architecture

  • Entry: src/index.ts selects stdio vs HTTP transport (src/transports.ts) by TRANSPORT.
  • Web server: src/server.web.ts + src/server/express.ts (WebMcpServer); web tools in src/tools/web/.
  • Desktop server: src/server.desktop.ts (DesktopMcpServer); discovers local Tableau Desktop via @modelcontextprotocol/ext-apps + DesktopDiscoverer; proxies through DesktopToolExecutor. Desktop tools in src/tools/desktop/.
  • SDK layer: src/sdks/tableau/ wraps the Tableau REST API (Zodios).
  • Cross-cutting: src/config.ts (auth: pat/uat/direct-trust/oauth), src/logging/ (PAT/token masking), src/telemetry/, src/server/oauth/, src/sessions.ts, src/errors/mcpToolError.ts.

Package manager

npm (lockfile package-lock.json). Node >=22.7.5 (engines). Do not switch package managers; do not commit a non-npm lockfile.

Commands

  • Install: npm ci (do not run inside an agent loop unless explicitly asked; never auto-install)
  • Build: npm run build (esbuild via tsx; does not typecheck)
  • Test (all, CI-safe): npx vitest run --config ./vitest.config.ts — never bare npm test (that is watch mode and hangs)
  • Test (single file): npx vitest run src/path/to/file.test.ts
  • Test (by name): npx vitest run src/path/to/file.test.ts -t "pattern"
  • Typecheck: npx tsc --noEmit (no typecheck npm script exists; build uses esbuild, so this is the only static type gate)
  • Lint: npm run lint (eslint)
  • Canonical check: scripts/agent-check

Read the full file on GitHub · 85 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. 2d ago First seen · 85 lines · 1,883 tokens per session scan A 46c55237cdc5

Subscribe to this mod's changes

tableau-mcp AGENTS.md is an instructions file published in the GitHub repository tableau/tableau-mcp (329 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,883 tokens to every session, about $0.0094 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planningmcpmcp-servermodelcontextprotocoltableau
Related

Other instructions, from other repositories

ida-pro-mcp CLAUDE.md

Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.

mrexodia/ida-pro-mcp · 1,135 tokens

pygwalker AGENTS.md

Instructions for Kanaries/pygwalker, covering agents.md — pygwalker contributor & agent guide, 1. what pygwalker is (30-second model), 2. repo map, 3. how the two halves fit together (build & load model) and 4. first-time setup.

Kanaries/pygwalker · 2,990 tokens

pygwalker CLAUDE.md

Instructions for Kanaries/pygwalker, covering claude.md and tl;dr for a coding agent.

Kanaries/pygwalker · 365 tokens

obot CLAUDE.md

Instructions for obot-platform/obot, covering claude.md, project overview, tech stack, common commands and development.

obot-platform/obot · 1,492 tokens

meilisearch-mcp CLAUDE.md

Instructions for meilisearch/meilisearch-mcp, covering claude.md, 🚨 important: development workflow guidelines, 🔄 fresh start protocol, 🎯 focused development rules and 📋 task assessment phase.

meilisearch/meilisearch-mcp · 2,670 tokens

MCP-Nest CLAUDE.md

Instructions for rekog-labs/MCP-Nest, covering claude.md, what this repo is, packages, layout and commands.

rekog-labs/MCP-Nest · 916 tokens