setup

setup is a command for coding agents from scalixworld/scalix-cloud-mcp. It costs 23 tokens per session (440 once invoked), scanned B, original, MIT.

A setup command for connecting a workspace to Scalix Cloud, a hosted platform for databases, AI, serverless functions, computing, storage, authentication, and billing.

In plain words
What is it for?
Use it to check for SCALIX_API_KEY, test the remote MCP endpoint, verify authentication, and optionally install the Scalix command-line tool.
Why use it?
It checks the API key and connection so configuration problems can be found before using the cloud tools.

Command

Part of the scalix plugin — 4 skills, 1 command, 2 MCP servers shipped together

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 commands/scalixworld/scalix-cloud-mcp/setup
Clone the repo
git clone --depth 1 https://github.com/scalixworld/scalix-cloud-mcp

Or install scalix, the plugin that ships this one along with the rest of its 4 skills, 1 command, 2 MCP servers.

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 setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/scalixworld/scalix-cloud-mcp/setup.svg)](https://agentmods.dev/commands/scalixworld/scalix-cloud-mcp/setup)
Your own site
<a href="https://agentmods.dev/commands/scalixworld/scalix-cloud-mcp/setup"><img src="https://agentmods.dev/badge/commands/scalixworld/scalix-cloud-mcp/setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 440 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 $0.00023 $0.00440
Opus 5 $0.00012 $0.00220
Sonnet 5 $0.00005 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 4d ago against content hash 2871e17616bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup 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 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

2. **Verify the endpoint.** Call the open MCP discovery (no auth needed): `curl -s -X POST https://api.scalix.world/v1/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'` and conf

Makes network callslowCapability

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

2. **Verify the endpoint.** Call the open MCP discovery (no auth needed): `curl -s -X POST https://api.scalix.world/v1/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'` and conf
commands/setup.md · 14 lines

What it actually says

Walk the user through connecting to Scalix Cloud. Follow these steps in order and report each result plainly:

  1. Check for a key. Look for SCALIX_API_KEY in the environment. If absent, tell the user to create one at https://console.scalix.world/org/keys?utm_source=claude-plugin&utm_medium=skill and export it as SCALIX_API_KEY. Never echo the key's value back.
  2. Verify the endpoint. Call the open MCP discovery (no auth needed): curl -s -X POST https://api.scalix.world/v1/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' and confirm a non-empty tool catalog comes back — 50 tools at the time of writing. Check that the list is there, not that it matches a number: the catalog changes, and the count in this file will lag it. This proves connectivity independent of the key. (The plain-HTTP GET /api/v1/mcp listing requires auth — don't use it for this step.)
  3. Verify the key. Make one authenticated call (for example POST https://api.scalix.world/api/v1/sql with {"query": "SELECT 1"}). A 401 means a bad or missing key — say so and stop; anything else confirms the connection.
  4. MCP tools. Remind the user this plugin already ships the MCP server config; after setting the env var they may need to restart Claude Code for the scalix server to connect.
  5. CLI (optional). If the user wants the terminal workflow: npm install -g scalix-cloud, then scalix-cloud login and scalix-cloud whoami.

If every step passes, summarise what is now available: 50 platform MCP tools, the REST API, and the CLI if installed.

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 · 14 lines · 23 tokens per session scan B 2871e17616bd

Subscribe to this mod's changes

setup is a command published in the GitHub repository scalixworld/scalix-cloud-mcp (2 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 440 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.