mcp-tool-implementation

mcp-tool-implementation is a cursor rule for Cursor from cuongtl1992/unleash-mcp. It costs 0 tokens per session (511 once invoked), scanned A, original, MIT.

Coding rules for implementing MCP tools, which let an AI assistant call defined functions through the Model Context Protocol.

In plain words
What is it for?
Use them when connecting an MCP tool to an Unleash integration and returning either formatted results or a structured error.
Why use it?
They standardise file placement, naming, handler structure, returned text, and error responses for new tools.

Cursor rule for Cursor

Written for Cursor: installed under .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/cuongtl1992/unleash-mcp/mcp-tool-implementation
Clone the repo
git clone --depth 1 https://github.com/cuongtl1992/unleash-mcp

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 mcp-tool-implementation

README.md
[![agentmods](https://agentmods.dev/badge/rules/cuongtl1992/unleash-mcp/mcp-tool-implementation.svg)](https://agentmods.dev/rules/cuongtl1992/unleash-mcp/mcp-tool-implementation)
Your own site
<a href="https://agentmods.dev/rules/cuongtl1992/unleash-mcp/mcp-tool-implementation"><img src="https://agentmods.dev/badge/rules/cuongtl1992/unleash-mcp/mcp-tool-implementation.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 511 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.00511
Opus 5 $0.00000 $0.00255
Sonnet 5 $0.00000 $0.00102
Haiku 4.5 $0.00000 $0.00051

Measured 6d ago against content hash e18b2e0b1b55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-tool-implementation 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 6d 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.

.cursor/rules/mcp-tool-implementation.mdc · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Implementation Guidelines

When implementing new MCP tools, follow these consistent patterns to maintain code quality and readability:

File Structure

  • Place all MCP tool implementations in the src/tools/ directory
  • Use kebab-case for filenames (e.g., get-projects.ts, update-flag.ts)
  • Name files according to their primary function

Implementation Pattern

  1. Import any necessary Unleash API integration functions:
import { requiredFunction } from '../unleash/required-function.js';
  1. Create a handler function with the naming convention handle[ToolName]:
async function handle[ToolName](mdc:parameters?: any) {
  try {
    const result = await requiredFunction(parameters);
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(result, null, 2),
        },
      ],
    };
  } catch (error: any) {
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(
            {
              success: false,
              error: error.message,
            },
            null,
            2
          ),
        },
      ],
      isError: true,
    };
  }
}
  1. Export the tool using a consistent structure:
export const toolName = {
  name: 'toolName',
  description: 'toolDescription',
  handler: handle[ToolName],
};

Error Handling

  • Always wrap API calls in try/catch blocks
  • Return a standardized error response object when errors occur:
    • Include isError: true flag
    • Include meaningful error messages
    • Maintain the consistent content structure

Response Format

  • Always return responses in the following format:
{
  content: [
    {
      type: 'text',
      text: string,
    },
    // More content items if needed
  ],
  isError?: boolean, // Include only for error responses
}

Parameter Handling

  • Define clear parameter types when needed
  • Validate parameters before using them in API calls
  • Handle missing parameters gracefully

Read the full file on GitHub · 96 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. 6d ago First seen · 96 lines · 0 tokens per session scan A e18b2e0b1b55

Subscribe to this mod's changes

mcp-tool-implementation is a cursor rule published in the GitHub repository cuongtl1992/unleash-mcp (11 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 511 tokens. 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 2026-08-31.