003_mcp

003_mcp is a cursor rule for Cursor from nwiizo/tfmcp. It costs 196 tokens per session, scanned A, original, MIT.

Guidelines for building an MCP server. MCP, or Model Context Protocol, is a standard way for AI tools to communicate with external resources and actions.

In plain words
What is it for?
Use it when implementing JSON-RPC communication over standard input and output, adding resource and prompt listings, integrating with Claude Desktop, supporting Terraform directory changes, and validating sensitive operations.
Why use it?
It helps keep messages, required methods, errors, logging, configuration, and safety checks consistent with the protocol.

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/nwiizo/tfmcp/003_mcp
Clone the repo
git clone --depth 1 https://github.com/nwiizo/tfmcp

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 003_mcp

README.md
[![agentmods](https://agentmods.dev/badge/rules/nwiizo/tfmcp/003_mcp.svg)](https://agentmods.dev/rules/nwiizo/tfmcp/003_mcp)
Your own site
<a href="https://agentmods.dev/rules/nwiizo/tfmcp/003_mcp"><img src="https://agentmods.dev/badge/rules/nwiizo/tfmcp/003_mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 196 This file is loaded in full into every session.
When invoked 196 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 $0.00196 $0.00196
Opus 5 $0.00098 $0.00098
Sonnet 5 $0.00039 $0.00039
Haiku 4.5 $0.00020 $0.00020

Measured 4d ago against content hash 721e383ddc78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

003_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 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.

.cursor/rules/003_mcp.mdc · 33 lines

What it actually says

MCP Protocol Implementation

Protocol Compliance

  • Follow the Model Context Protocol specification.
  • Implement required methods like resources/list and prompts/list.
  • Ensure proper JSON-RPC 2.0 formatting for all messages.
  • Handle protocol errors gracefully.

Server Implementation

  • Use stdin/stdout for communication in MCP server mode.
  • Implement proper error handling and response formatting.
  • Provide meaningful error messages for debugging.
  • Log MCP interactions appropriately.

Claude Desktop Integration

  • Ensure seamless integration with Claude Desktop.
  • Set up proper environment variables for Claude Desktop.
  • Support changing terraform directories at runtime.
  • Document integration steps clearly.

Security Considerations

  • Implement appropriate safeguards for sensitive operations.
  • Consider permission boundaries for terraform operations.
  • Validate inputs to prevent command injection.
  • Add safety mechanisms like confirmation prompts for destructive operations.
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 · 33 lines · 196 tokens per session scan A 721e383ddc78

Subscribe to this mod's changes

003_mcp is a cursor rule published in the GitHub repository nwiizo/tfmcp (371 stars, last pushed today), licensed MIT. It adds 196 tokens to every session, about $0.0010 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.