A guide for creating MCP server integrations. MCP is a standard way for an agent to connect to outside tools such as Notion, a browser, or workflow software.

Use it when adding a new MCP server, defining its tools and arguments, reading tool descriptors, and connecting the agent to existing services.

It gives developers a consistent folder layout and tool description format, making integrations easier to discover and call correctly.

mcp-server — Skill for Claude Code and Codex by WellApp-ai/Well

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.

Any agent

npx skills add WellApp-ai/Well --skill mcp-server

Clone the repo

git clone --depth 1 https://github.com/WellApp-ai/Well

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wellapp-ai/well/mcp-server/github.svg)](https://agentmods.dev/skills/wellapp-ai/well/mcp-server)

Your own site

<a href="https://agentmods.dev/skills/wellapp-ai/well/mcp-server"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wellapp-ai/well/mcp-server"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 759 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 74
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.00759
Opus 5.5	$0.00004	$0.00304
Sonnet 5.5	$0.00002	$0.00152
Haiku 4.5	$0.00001	$0.00076

Measured 1mo ago against content hash 6044313b7117, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server 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 1mo 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/skills/mcp-server/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Creation Guide

Use this skill when creating a new MCP server integration.

MCP Folder Structure

MCPs live in: ~/.cursor/projects/<project>/mcps/<server-name>/

mcps/
├── user-notion/
│   └── tools/
│       ├── API-retrieve-a-page.json
│       └── ...
├── cursor-ide-browser/
│   └── tools/
│       ├── browser_navigate.json
│       └── ...
└── user-n8n-mcp/
    └── tools/
        └── ...

Tool Descriptor Format

Each tool is a JSON file:

{
  "name": "tool-name",
  "description": "What this tool does",
  "arguments": {
    "type": "object",
    "properties": {
      "param1": { "type": "string", "description": "..." }
    },
    "required": ["param1"]
  }
}

Usage Pattern

Read tool descriptor before calling
Use CallMcpTool with server, toolName, arguments
Handle response appropriately

Example Call

CallMcpTool:
  server: "user-notion"
  toolName: "API-retrieve-a-page"
  arguments: { "page_id": "abc123" }

Existing MCPs Reference

MCP	Capabilities
user-notion	Page/block CRUD, search, comments
cursor-ide-browser	Navigation, clicks, screenshots, console
user-n8n-mcp	Workflow search, details, execution
user-context7	Library docs lookup
figma	Design specs, code generation from frames

Creating a New MCP

Create folder: mcps/<server-name>/tools/
Add tool descriptors as JSON files
Configure server in ~/.cursor/mcp.json
Restart Cursor (Cmd+Shift+P > "Reload Window")
Test with CallMcpTool

Authentication Patterns

Pattern 1: API Token (env block)

For MCPs that use API keys (Notion, n8n):

"mcp-name": {
  "command": "npx",
  "args": ["-y", "@package/mcp-server"],
  "env": {
    "API_KEY": "your-token-here"
  }
}

Pattern 2: URL-based (no auth)

For MCPs that connect to local servers (Figma desktop):

"mcp-name": {
  "url": "http://127.0.0.1:PORT/mcp"
}

Pattern 3: OAuth (remote URL)

Read the full file on GitHub · 135 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.

1mo ago First seen · 135 lines · 11 tokens per session scan A 6044313b7117

Subscribe to this mod's changes

mcp-server is a skill published in the GitHub repository WellApp-ai/Well (345 stars, last pushed 6d ago), licensed MIT. It adds 11 tokens to every session and 759 once invoked, about $0.0000 per session on Opus 5.5. 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.

Building agents ai api automation finops invoice invoice-extraction

auto-reader-ocr

Extract text from images/PDFs (Arabic-first, manga-aware Japanese, 13+ languages auto-detected), translate between 100+ languages, and pull structured fields from invoices/receipts/IDs via the Auto-Reader OCR API. Use when the user shares a document image or PDF to read, translate, or extract data from — or asks for…

Samqra/auto-reader-ocr · 101 tokens

api-integration-architect

Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.

sickn33/agentic-awesome-skills · 33 tokens

non-json-content-types

Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).

trpc/trpc · 75 tokens

mirrord-prev-env

Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…

metalbear-co/mirrord · 122 tokens

horse-integration-tests

Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.

HashLoad/horse · 25 tokens

smoke-test

Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.

Skyvern-AI/skyvern · 50 tokens