04-mcp-tools

04-mcp-tools is a cursor rule for coding agents from WellApp-ai/Well. It costs 2,437 tokens per session, scanned A, original, MIT.

A set of instructions for using MCP tools—connections that let an agent work with services such as Notion, browsers, n8n, Context7, and Figma. It also directs the agent to consult Context7 for current library and framework documentation.

In plain words
What is it for?
Use it when working with the listed services, checking unfamiliar APIs, handling recent library changes, or investigating library-specific errors.
Why use it?
It reduces guesswork when an agent needs outside tools or up-to-date instructions for a software library.

Cursor rule

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/wellapp-ai/well/04-mcp-tools
Clone the repo
git clone --depth 1 https://github.com/WellApp-ai/Well

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 04-mcp-tools

README.md
[![agentmods](https://agentmods.dev/badge/rules/wellapp-ai/well/04-mcp-tools.svg)](https://agentmods.dev/rules/wellapp-ai/well/04-mcp-tools)
Your own site
<a href="https://agentmods.dev/rules/wellapp-ai/well/04-mcp-tools"><img src="https://agentmods.dev/badge/rules/wellapp-ai/well/04-mcp-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,437 This file is loaded in full into every session.
When invoked 2,437 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 $0.02437 $0.02437
Opus 5 $0.01218 $0.01218
Sonnet 5 $0.00487 $0.00487
Haiku 4.5 $0.00244 $0.00244

Measured 5d ago against content hash 4987cbdbca67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

04-mcp-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 5d 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/rules/04-mcp-tools.mdc · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tools

Context7 MCP

Always use Context7 MCP for library/framework docs before implementing features or fixing issues.

Usage:

  1. Use resolve-library-id tool with libraryName parameter to find the library ID
  2. Use get-library-docs tool with the resolved context7CompatibleLibraryID and optional topic
  3. Modes: mode='code' (API/code, default), mode='info' (concepts/architecture)

Common Libraries:

  • Next.js (/vercel/next.js): Routing, SSR, app architecture
  • React (/facebook/react): Component patterns, hooks
  • MikroORM (/mikro-orm/mikro-orm): Database operations, entities
  • TanStack Query (/tanstack/query): Data fetching, caching
  • Radix UI (/radix-ui/primitives): UI component patterns
  • Tailwind CSS (/tailwindlabs/tailwindcss): Styling patterns
  • Zod (/colinhacks/zod): Schema validation
  • Express (/expressjs/express): API routing, middleware
  • Framer Motion (/framer/motion): Animations
  • React Hook Form (/react-hook-form/react-hook-form): Form handling

When to use: Unsure about API syntax, recent library updates, unfamiliar features, library-specific errors Skip for: Basic React/TypeScript patterns, simple Tailwind classes, standard Next.js routing, trivial tasks

Notion MCP

On init mode:

  • Verify working directory is clean before branching
  • Clear build caches to prevent cross-branch contamination

On branch creation:

  • Update "Branch name" field in Notion task

On PR push:

  • Add full plan content to Notion page body
  • Update "Github PR link" field with PR URL

On feature lookup:

  • Fetch task details before starting work

Key tools:

  • API-retrieve-a-page - Get task details

  • API-get-block-children - Get page content

  • API-post-search - Search across workspace (fallback for database queries)

  • API-patch-page - Update page properties

  • API-patch-block-children - Add content to page

Known Issues:

Read the full file on GitHub · 300 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. 5d ago First seen · 300 lines · 2,437 tokens per session scan A 4987cbdbca67

Subscribe to this mod's changes

04-mcp-tools is a cursor rule published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 28d ago), licensed MIT. It adds 2,437 tokens to every session, about $0.0122 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.