What is scylladb-cloud-mcp?

A connection between an AI agent and ScyllaDB Cloud, a managed database service for applications. It helps the agent work with ScyllaDB Cloud clusters through the MCP server, which is currently read-only.

Use it to configure the ScyllaDB Cloud MCP server, connect an agent to ScyllaDB Cloud, and create or monitor clusters where the available read-only tools support those tasks.

It gives an AI agent a defined way to inspect and manage ScyllaDB Cloud instead of requiring custom integration code. Because it is read-only, it cannot yet make changes to clusters.

scylladb-cloud-mcp — Skill for Claude Code by scylladb/agent-skills

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 scylladb/agent-skills --skill scylladb-cloud-mcp

Clone the repo

git clone --depth 1 https://github.com/scylladb/agent-skills

Made for: Claude Code.

Or install scylladb, the plugin that ships this one along with the rest of its 8 skills.

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/scylladb/agent-skills/scylladb-cloud-mcp/github.svg)](https://agentmods.dev/skills/scylladb/agent-skills/scylladb-cloud-mcp)

Your own site

<a href="https://agentmods.dev/skills/scylladb/agent-skills/scylladb-cloud-mcp"><img src="https://agentmods.dev/badge/skills/scylladb/agent-skills/scylladb-cloud-mcp/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/scylladb/agent-skills/scylladb-cloud-mcp"><img src="https://agentmods.dev/badge/skills/scylladb/agent-skills/scylladb-cloud-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 839 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.

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	$0.00136	$0.00839
Opus 5.5	$0.00054	$0.00336
Sonnet 5.5	$0.00027	$0.00168
Haiku 4.5	$0.00014	$0.00084

Measured 21d ago against content hash a48f31344a05, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scylladb-cloud-mcp 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 21d 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.

skills/scylladb-cloud-mcp/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ScyllaDB Cloud MCP Server

If the task goes beyond this skill, use the parent scylladb skill for a ScyllaDB overview and the list of other ScyllaDB skills. If it is not installed, fetch it from https://raw.githubusercontent.com/scylladb/agent-skills/main/skills/scylladb/SKILL.md.

The ScyllaDB Cloud MCP server exposes the ScyllaDB Cloud API as tools that AI agents can call. The server is in beta.

When to Use This Skill

The user wants to add the ScyllaDB Cloud MCP server to Claude Code, Cursor, or another MCP client
The user wants an AI agent to create, delete, or monitor ScyllaDB Cloud clusters
The user needs an API token for the MCP server, or committed a token by mistake
The user is building an agentic workflow that manages ScyllaDB Cloud resources

For adjacent topics, use the sibling skill instead:

Connecting an application to a cluster with a CQL driver, or provisioning clusters with Terraform: scylladb-cloud-setup
Self-managed clusters on Kubernetes: scylladb-kubernetes

Setup

Fetch the MCP documentation for the server URL, the tool list, and the client configuration: https://cloud.docs.scylladb.com/stable/api-docs/mcp.md
Guide the user to create a personal API token: https://cloud.docs.scylladb.com/stable/api-docs/create-api-token.md
Help the user add the server to their MCP client. Keep the token out of git (see below).
Ask the client to list the scylladb-cloud tools to confirm the setup.

For Claude Code, use this command:

claude mcp add --transport http scylladb-cloud https://mcp.cloud.scylladb.com \
  --header "Authorization: Bearer ${SCYLLADB_CLOUD_API_TOKEN}"

The default local scope stores the token in ~/.claude.json.

Keep the Token out of Git

The token gives access to the user's ScyllaDB Cloud account. Never write the token value into a file that is committed to git.

Store the token in an environment variable, for example SCYLLADB_CLOUD_API_TOKEN, and reference the variable from the MCP client configuration.
Prefer user-level or local MCP configuration over project-level files that are committed (such as .mcp.json or .cursor/mcp.json).
If the token must be in a file inside the repository, add that file to .gitignore before the user saves the token.
If a token was committed, tell the user to revoke it in Settings > Personal Tokens and create a new one. Removing it from git history is not enough.

Read the full file on GitHub · 57 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.

21d ago Changed · +46 lines · +18 tokens per session a48f31344a05
2mo ago First seen · 11 lines · 118 tokens per session scan A 1717852f9942

Subscribe to this mod's changes

scylladb-cloud-mcp is a skill published in the GitHub repository scylladb/agent-skills (9 stars, last pushed 9d ago), licensed Apache-2.0. It adds 136 tokens to every session and 839 once invoked, about $0.0005 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 2026-08-31.

Cloud Databases DevOps and cloud cql nosql scylla scylladb skills

scylladb-cloud-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
scylladb-cloud-mcpscylladb/agent-skills	Skill	9	9d ago	Apache-2.0	A	136	Claude Code
bigquery-migration-sql-translatorgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	132	Claude Code, Codex
cloud-databases-onboardinggoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
google-cloud-storage-fusegoogle/skills	Skill	22k	yesterday	Apache-2.0	A	225	Claude Code, Codex
cloud-sql-basicsgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	108	Claude Code, Codex
confluent-cloud-cdc-tableflowconfluentinc/agent-skills	Skill	61	10d ago	Apache-2.0	A	203	Claude Code
doris-debug-cloudapache/doris-skills	Skill	49	2d ago	Apache-2.0	A	40	Claude Code, Codex