deployment-guide

deployment-guide is a cursor rule for Cursor from Kenlan2022/mcp_servers_showcase. It costs 0 tokens per session (2,284 once invoked), scanned B, original, MIT.

A deployment checklist and guide for MCP servers, covering code checks, documentation, configuration, environment setup, and release installation. MCP servers provide tools that an AI assistant can call.

In plain words
What is it for?
Testing, formatting, type-checking, linting, documenting, configuring, and installing a Python-based MCP server for deployment.
Why use it?
It turns deployment preparation into concrete checks and helps catch incomplete documentation, unsafe settings, or failing code.

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/kenlan2022/mcp_servers_showcase/deployment-guide
Clone the repo
git clone --depth 1 https://github.com/Kenlan2022/mcp_servers_showcase

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 deployment-guide

README.md
[![agentmods](https://agentmods.dev/badge/rules/kenlan2022/mcp_servers_showcase/deployment-guide.svg)](https://agentmods.dev/rules/kenlan2022/mcp_servers_showcase/deployment-guide)
Your own site
<a href="https://agentmods.dev/rules/kenlan2022/mcp_servers_showcase/deployment-guide"><img src="https://agentmods.dev/badge/rules/kenlan2022/mcp_servers_showcase/deployment-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,284 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00000 $0.02284
Opus 5 $0.00000 $0.01142
Sonnet 5 $0.00000 $0.00457
Haiku 4.5 $0.00000 $0.00228

Measured 3d ago against content hash 75d9a90fda19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

deployment-guide scanned grade B with 2 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo systemctl daemon-reload

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -f http://localhost:8000/health || echo "Server not responding"
.cursor/rules/deployment-guide.mdc · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Deployment Guide

Pre-deployment Checklist

Code Quality Check

  • All tests passing (uv run pytest)
  • Code formatted (uv run black .)
  • Imports sorted (uv run isort .)
  • Type checking passes (uv run mypy .)
  • Linting passes (uv run ruff check .)
  • No TODO comments remain in code
  • All security vulnerabilities addressed

Documentation Check

  • README.md updated with current functionality
  • API documentation complete
  • Configuration options documented
  • Usage examples provided
  • TODO.md reflects actual state

Configuration Validation

  • Environment variables documented
  • Configuration file templates provided
  • Default values are secure
  • Sensitive data properly handled
  • Connection strings validated

Deployment Process

Step 1: Environment Setup

# Create deployment directory
mkdir -p /opt/mcp-servers
cd /opt/mcp-servers

# Clone repository
git clone <repository-url> .
git checkout <release-tag>

# Setup Python environment with UV
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt

Step 2: Configuration

# Copy configuration template
cp config.template.toml config.toml

# Edit configuration
nano config.toml

Configuration Template:

[server]
host = "0.0.0.0"
port = 8000
debug = false
workers = 4

[database]
path = "/data/mcp_servers.db"
max_connections = 20
backup_interval = 3600  # seconds

[file_server]
base_directory = "/data/files"
max_file_size = 10485760  # 10MB
allowed_extensions = [".txt", ".json", ".csv", ".md"]

[logging]
level = "INFO"
file = "/var/log/mcp-servers.log"
rotate_size = 10485760  # 10MB
backup_count = 5

Step 3: Database Setup

# Create database directory
mkdir -p /data
chmod 750 /data

# Initialize database (if needed)
uv run python -c "
import asyncio
from servers.db_server.database import initialize_database
asyncio.run(initialize_database('/data/mcp_servers.db'))
"

Read the full file on GitHub · 449 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. 3d ago First seen · 449 lines · 0 tokens per session scan B 75d9a90fda19

Subscribe to this mod's changes

deployment-guide is a cursor rule published in the GitHub repository Kenlan2022/mcp_servers_showcase (0 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,284 tokens. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.