mcp

mcp is a cursor rule for Cursor from umijs/umi-mcp. It costs 269 tokens per session, scanned A, original, MIT.

A set of rules for implementing MCP tools, which are functions an AI assistant can call through the Model Context Protocol. It defines where tools belong, how their inputs and outputs are described, and how they should validate errors.

In plain words
What is it for?
Use it when adding or reviewing tools in the src/tools directory: define schemas with zod, keep each tool focused, document it, handle errors clearly, and export it from src/index.ts.
Why use it?
It gives tool developers a consistent structure, making tools easier to discover, call, test, and maintain. Input validation and descriptive errors also make failures clearer.

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/umijs/umi-mcp/mcp
Clone the repo
git clone --depth 1 https://github.com/umijs/umi-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

README.md
[![agentmods](https://agentmods.dev/badge/rules/umijs/umi-mcp/mcp.svg)](https://agentmods.dev/rules/umijs/umi-mcp/mcp)
Your own site
<a href="https://agentmods.dev/rules/umijs/umi-mcp/mcp"><img src="https://agentmods.dev/badge/rules/umijs/umi-mcp/mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 269 This file is loaded in full into every session.
When invoked 269 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 $0.00269 $0.00269
Opus 5 $0.00134 $0.00134
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 4d ago against content hash 8060c1ea0e25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/mcp.mdc · 35 lines

What it actually says

MCP Tools Implementation

Tool Structure

  • All MCP tools should follow a consistent structure
  • Each tool is defined in src/tools/ with a prefix of umi-
  • Tools should export a function that returns a Tool object
  • Tools should define input and output schemas

Input/Output Schemas

  • Define input schemas using zod
  • Define output schemas to match expected return values
  • Follow MCP spec for schema definitions
  • Use descriptive names for schema properties

Error Handling

  • Use proper error handling with descriptive messages
  • Return structured error responses when appropriate
  • Validate inputs before processing

Tool Implementation

  • Keep tool implementations focused on a single responsibility
  • Reuse common code for similar tools (like config management)
  • Document tools with clear descriptions
  • Export tools in the src/index.ts file for consumption

Examples

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 · 35 lines · 269 tokens per session scan A 8060c1ea0e25

Subscribe to this mod's changes

mcp is a cursor rule published in the GitHub repository umijs/umi-mcp (21 stars, last pushed 1y ago), licensed MIT. It adds 269 tokens to every session, about $0.0013 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.