tools

tools is a cursor rule for Cursor from marcushojww/tableau-mcp-v2. It costs 0 tokens per session (886 once invoked), scanned A, a copy of tools, Apache-2.0.

A set of coding rules for building MCP tools, which are tools that let an AI assistant call functions in another program. It covers factories, shared base classes, callbacks, registration, and access scopes.

In plain words
What is it for?
Use it when creating tool directories, defining input schemas, implementing callbacks, registering tools, and configuring their permission scopes.
Why use it?
It gives developers a consistent checklist and structure when adding a new tool to an MCP server.

Cursor rule for Cursor

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/marcushojww/tableau-mcp-v2/tools
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.

agentmods badge for tools

README.md
[![agentmods](https://agentmods.dev/badge/rules/marcushojww/tableau-mcp-v2/tools.svg)](https://agentmods.dev/rules/marcushojww/tableau-mcp-v2/tools)
Your own site
<a href="https://agentmods.dev/rules/marcushojww/tableau-mcp-v2/tools"><img src="https://agentmods.dev/badge/rules/marcushojww/tableau-mcp-v2/tools.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 886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% 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 $0.00000 $0.00886
Opus 5 $0.00000 $0.00443
Sonnet 5 $0.00000 $0.00177
Haiku 4.5 $0.00000 $0.00089

Measured 4d ago against content hash cc3087876605, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools 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

97% identical to tools — 2 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/tools.mdc · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool Development Patterns

Factory Pattern

Every tool exports a factory function registered in src/tools/tools.ts:

export const getMyTool = (server: Server): Tool<typeof paramsSchema> => {
  const myTool = new Tool({
    server,
    name: 'my-tool',           // Must be in ToolName union (src/tools/toolName.ts)
    description: '...',
    paramsSchema,               // Zod schema object (not z.object, just raw shape)
    annotations: { title: 'My Tool', readOnlyHint: true, openWorldHint: false },
    callback: async (args, extra) => { ... },
  });
  return myTool;
};

Adding a New Tool — Checklist

  1. Add tool name to toolNames array in src/tools/toolName.ts
  2. Add to appropriate toolGroups entry (or create new group)
  3. Add scope mapping in src/server/oauth/scopes.ts (toolScopeMap)
  4. Create tool directory under src/tools/
  5. Implement factory function following the pattern above
  6. Register factory in src/tools/tools.ts (toolFactories array)

Tool Callback Pattern

Callbacks use logAndExecute from the base Tool class:

callback: async (args, extra): Promise<CallToolResult> => {
  return await myTool.logAndExecute({
    extra,
    args,
    callback: async () => {
      const result = await useRestApi({
        ...extra,
        jwtScopes: myTool.requiredApiScopes,
        callback: async (restApi) => {
          // Use restApi methods here
          return data;
        },
      });
      return new Ok(result);     // ts-results-es Ok()
    },
    constrainSuccessResult: (result) => constrainMyResult(result),
  });
},

Result Types

  • Result<T, E> from ts-results-es — tool callbacks return this
  • Ok(value) for success, Err(error) for typed errors
  • ConstrainedResult<T> — post-processing step with three outcomes:
    • { type: 'success', result: T } — data returned to client
    • { type: 'empty', message: string } — no data found (not an error)
    • { type: 'error', message: string, error?: Error } — logical error

Read the full file on GitHub · 98 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 · 98 lines · 0 tokens per session scan A cc3087876605

Subscribe to this mod's changes

tools 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 886 tokens. A static security scan graded it A with 0 findings. It is 97% identical to tools, differing in 2 lines, and is treated as a copy.