mcp-conventions

mcp-conventions is a cursor rule for Cursor from bowen31337/expressjs_mcp. It costs 6 tokens per session (311 once invoked), scanned A, original, MIT.

A set of rules for designing MCP tools and HTTP endpoints consistently. It defines naming, schemas, examples, routes, authentication, and success and error responses.

In plain words
What is it for?
It is for implementing or reviewing MCP tool definitions, OpenAPI-based schemas, gateway endpoints, and authentication handling.
Why use it?
It prevents different tools from exposing incompatible names, inputs, outputs, or security behaviour.

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/bowen31337/expressjs_mcp/mcp-conventions
Clone the repo
git clone --depth 1 https://github.com/bowen31337/expressjs_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-conventions

README.md
[![agentmods](https://agentmods.dev/badge/rules/bowen31337/expressjs_mcp/mcp-conventions.svg)](https://agentmods.dev/rules/bowen31337/expressjs_mcp/mcp-conventions)
Your own site
<a href="https://agentmods.dev/rules/bowen31337/expressjs_mcp/mcp-conventions"><img src="https://agentmods.dev/badge/rules/bowen31337/expressjs_mcp/mcp-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 311 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 $0.00006 $0.00311
Opus 5 $0.00003 $0.00156
Sonnet 5 $0.00001 $0.00062
Haiku 4.5 $0.00001 $0.00031

Measured 4d ago against content hash 27b6e93a027a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-conventions 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/mcp-conventions.mdc · 47 lines

What it actually says

MCP Tool Conventions

Tool Naming

  • title: Human-readable format like "GET /users"
  • name: Safe identifier format like "GET_/users" (spaces → underscores)

Schema Structure

Tools must have consistent schema structure:

{
  name: string,           // Safe identifier
  title: string,          // Human readable
  description: string,    // What the tool does
  inputSchema: object,    // JSON Schema for input
  outputSchema: object,   // JSON Schema for output
  examples: any[],        // Usage examples
  route: { method, path } // Original Express route info
}

HTTP Gateway Endpoints

  • GET /mcp/tools - List all available tools
  • POST /mcp/invoke - Invoke a tool with { toolName, args }

Response Format

Invocation responses follow this pattern:

// Success
{ ok: true, result: any, status: number }

// Error
{ ok: false, error: string }

Schema Priority

  1. Per-route zod annotations (schemaAnnotations)
  2. OpenAPI v3 specification (openapi option)
  3. Permissive fallback ({ type: 'object', additionalProperties: true })

Auth Integration

  • Reuse existing Express middleware chain
  • No bypass of authentication/authorization
  • Preserve 401/403 responses from middleware
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 · 47 lines · 6 tokens per session scan A 27b6e93a027a

Subscribe to this mod's changes

mcp-conventions is a cursor rule published in the GitHub repository bowen31337/expressjs_mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 6 tokens to every session and 311 once invoked, about $0.0000 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 2026-08-31.