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.
npx agentmods add instructions/sota-deploy/mcp-server/claude-mdgit clone --depth 1 https://github.com/sota-deploy/mcp-serverWrote 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.
[](https://agentmods.dev/instructions/sota-deploy/mcp-server/claude-md)<a href="https://agentmods.dev/instructions/sota-deploy/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sota-deploy/mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01599 | $0.01599 |
| Opus 5 | $0.00800 | $0.00800 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
mcp-server CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sota.io MCP Server — AI Agent Context
This file provides AI agents with context about the sota.io platform when using the MCP server.
Platform Overview
sota.io is an EU-native DevOps PaaS. Deploy any web app and get a live URL at {slug}.sota.io.
Every Project Includes
- Managed PostgreSQL 17 —
DATABASE_URLis auto-injected into your container. No setup needed. - PgBouncer connection pooling — Pool size 20, max 100 client connections.
- Daily database backups — 7-day retention, automatic.
- Automatic HTTPS — Let's Encrypt wildcard certificate.
- Zero-downtime deploys — Blue-green strategy with instant rollback.
- Container isolation — gVisor sandboxing.
- EU hosting — Hetzner Cloud, Germany. GDPR-compliant.
Supported Frameworks
| Framework | Detection | Notes |
|---|---|---|
| Next.js | next.config.js/ts |
Add output: 'standalone' for best results |
| Node.js | package.json with start script |
Express, Fastify, Koa, Hapi, etc. |
| Python | requirements.txt or pyproject.toml |
Flask, FastAPI, Django |
| Custom | Dockerfile in project root |
Go, Rust, Java, Ruby, PHP, anything. Port auto-detected from EXPOSE directive. |
Your app MUST listen on process.env.PORT. For auto-detected frameworks (Next.js, Node.js, Python), PORT is 8080. For custom Dockerfiles, the port is auto-detected from the EXPOSE directive (e.g., EXPOSE 3000 sets PORT=3000). If no EXPOSE is found, it defaults to 8080.
Database — How It Works
- Create a project → PostgreSQL 17 database is auto-provisioned.
- Deploy your app →
DATABASE_URLis injected into the container. - Your app reads
DATABASE_URLfrom the environment — that's it.
You do NOT need to:
- Set
DATABASE_URLmanually - Provision a database
- Configure connection strings
- Set up SSL for the database (internal network, sslmode=disable is safe)
If your app needs tables, run migrations on startup — there is no shell access to containers. Chain the migration command before your server start:
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.
- 4d ago First seen · 134 lines · 1,599 tokens per session scan A dbd49cc56e88
mcp-server CLAUDE.md is an instructions file published in the GitHub repository sota-deploy/mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,599 tokens to every session, about $0.0080 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.
Other instructions, from other repositories
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.
equinix-fabric-mcp CLAUDE.md
Claude Code instructions for sliuuu/equinix-fabric-mcp, covering claude.md — equinix-fabric-mcp, canonical files, auth, add equinixclientid and equinixclientsecret and running.
CopilotInstructions bicep.instructions.md
Instructions for jschick04/CopilotInstructions, covering bicep infrastructure-as-code instructions, bicep standards and bicep recurring smells.
lambda_cloud_MCP CLAUDE.md
Claude Code instructions for dankit/lambda_cloud_MCP, a project described as: GPU availability tracker with alerting & auto-provisioning right as they become available. MCP for agentic handling of environment setups. Fully orchestrated via text message with Poke.