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 skills add umbraco/Umbraco-CMS-MCP-Dev --skill umb-cms-mcp-setupgit clone --depth 1 https://github.com/umbraco/Umbraco-CMS-MCP-DevWrote 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/skills/umbraco/umbraco-cms-mcp-dev/umb-cms-mcp-setup)<a href="https://agentmods.dev/skills/umbraco/umbraco-cms-mcp-dev/umb-cms-mcp-setup"><img src="https://agentmods.dev/badge/skills/umbraco/umbraco-cms-mcp-dev/umb-cms-mcp-setup/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.
<a href="https://agentmods.dev/skills/umbraco/umbraco-cms-mcp-dev/umb-cms-mcp-setup"><img src="https://agentmods.dev/badge/skills/umbraco/umbraco-cms-mcp-dev/umb-cms-mcp-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Agent Snooping · line 30 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
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 | $0.00068 | $0.01790 |
| Opus 5 | $0.00034 | $0.00895 |
| Sonnet 5 | $0.00014 | $0.00358 |
| Haiku 4.5 | $0.00007 | $0.00179 |
Grade B, and why
umb-cms-mcp-setup scanned grade B with 1 finding 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 9d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
When the client is a coding agent working against a project (Claude Code, Cursor, VS Code, etc.), the preferred setup is a project-scoped MCP config file — e.g. `.mcp.json` for Claude Code — rather than a global/user-lev How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Umbraco MCP Server — Setup Guide
This covers running @umbraco-cms/mcp-dev as a live MCP server connected to an AI client (Claude Desktop, Claude Code, Cursor, VS Code, etc). For debugging the package directly on the command line (--list-tools, --call, --debug-config), see the umb-cms-dev-cli skill instead — the same env vars apply either way.
For install steps, verifying the connection, and troubleshooting, use the official docs rather than this skill — they're the source of truth and won't drift out of sync the way a duplicated copy here would:
For per-client configuration, go straight to the guide for the client actually in use rather than the general page above:
Prerequisites
- An Umbraco CMS instance the client can reach over HTTPS (or HTTP on a local network).
- Node.js 22 or later (the package's declared
engines.noderequirement) if the client itself needs to runnpx— most desktop clients bundle their own Node runtime, so this mainly matters if you're invoking the server manually. - An Umbraco API user with the permissions you want the agent to have — see Umbraco's API user documentation. You'll come away with a client ID and client secret; treat the secret like a password (never commit it, never paste it into chat).
Coding Environments: .mcp.json
When the client is a coding agent working against a project (Claude Code, Cursor, VS Code, etc.), the preferred setup is a project-scoped MCP config file — e.g. .mcp.json for Claude Code — rather than a global/user-level config, so the server definition can be checked in and shared across the team without each developer's real secrets:
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.
- 9d ago First seen · 85 lines · 68 tokens per session scan B 9e0c944e8fa0
umb-cms-mcp-setup is a skill published in the GitHub repository umbraco/Umbraco-CMS-MCP-Dev (39 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 1,790 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…