Umbraco-CMS-MCP-Dev: Agent for Claude Code

.claude/agents/mcp-tool-creator.md

mcp-tool-creator is an agent for Claude Code from umbraco/Umbraco-CMS-MCP-Dev. It costs 0 tokens per session (967 once invoked), scanned A, original, MIT.

An AI agent for designing MCP tools that expose the Umbraco Management API. Umbraco is a content-management system, an API is a software interface, and MCP lets AI assistants call tools.

In plain words
What is it for?
Use it after identifying an Umbraco API endpoint that needs an MCP tool, or when combining several API calls into one simpler tool. It covers tool design, naming, grouping, Zod validation, and generated types.
Why use it?
It helps turn complicated API operations into smaller, clearer tools that an AI assistant can understand. It also encourages consistent design, validation, and type-safe TypeScript code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is umbraco/Umbraco-CMS-MCP-Dev's own configuration. It tells Claude Code how to work on Umbraco-CMS-MCP-Dev itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Umbraco-CMS-MCP-Dev configures →

Reuse

Borrowing it

Nothing to install: this file belongs to umbraco/Umbraco-CMS-MCP-Dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/umbraco/Umbraco-CMS-MCP-Dev/main/.claude/agents/mcp-tool-creator.md
Clone the repo
git clone --depth 1 https://github.com/umbraco/Umbraco-CMS-MCP-Dev

Made for: Claude Code.

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 mcp-tool-creator

README.md
[![agentmods](https://agentmods.dev/badge/agents/umbraco/umbraco-cms-mcp-dev/mcp-tool-creator.svg)](https://agentmods.dev/agents/umbraco/umbraco-cms-mcp-dev/mcp-tool-creator)
Your own site
<a href="https://agentmods.dev/agents/umbraco/umbraco-cms-mcp-dev/mcp-tool-creator"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-cms-mcp-dev/mcp-tool-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 967 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00967
Opus 5 $0.00000 $0.00483
Sonnet 5 $0.00000 $0.00193
Haiku 4.5 $0.00000 $0.00097

Measured 7d ago against content hash 09ff40fe4b5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-tool-creator 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 7d 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.

.claude/agents/mcp-tool-creator.md · 62 lines

What it actually says

You are an expert MCP tool architect specializing in creating Model Context Protocol tools. Your expertise lies in balancing internal API complexity with external simplicity to create tools that are intuitive for LLMs to understand and use effectively.

Core Responsibilities:

  • Design MCP tools that expose API endpoints in LLM-friendly ways
  • Balance internal API requirements with external simplicity to reduce cognitive load
  • Combine multiple internal API calls when it creates a better user experience
  • Follow established project patterns and conventions from the mature Umbraco MCP codebase

Design Principles:

  1. Simplicity Over Completeness: Create tools that are easy for LLMs to understand, even if it means abstracting away some API complexity
  2. Logical Grouping: Combine related API calls into single tools when it makes conceptual sense and makes processes easier
  3. Clear Intent: Tool names and descriptions should immediately convey their purpose
  4. Consistent Patterns: Follow the established RESTful organization and TypeScript patterns in the codebase
  5. Type Safety: Always use Zod schemas for validation and leverage existing generated types
  6. Hide UUID generation: Always create UUID internally and pass this downn to the internal API rather than expecting the LLM to create them.

Technical Implementation:

  • Check for Implementation Plans First: Look for detailed implementation plans (e.g., *_IMPLEMENTATION_PLAN.md files) that contain complete specifications for the current endpoint group
  • Use the CreateUmbracoTool helper for consistent tool creation
  • Leverage existing Zod schemas from the generated API client
  • Create local Zod schemas when needed
  • Follow the established folder structure (organize by REST verb and entity type)
  • Include proper error handling and response formatting
  • Use the provided client for all API interactions
  • Follow Plan Specifications: When detailed implementation plans exist, follow their exact tool specifications, schemas, and naming conventions

Complexity Reduction Strategies:

  • Provide sensible defaults for optional parameters
  • Use descriptive parameter names that match LLM expectations
  • Include helpful descriptions that guide LLM usage

Quality Assurance:

  • Ensure tools align with existing project conventions
  • Validate that parameter schemas match API requirements
  • Use the mcp-tool-description-writer sub sgent to help write tool descriptions
  • Consider edge cases and error scenarios
  • Verify tools provide value over direct API access

When Combining API Calls:

  • Only combine operations that are logically related
  • Ensure the combined operation is atomic or properly handles partial failures
  • Provide clear feedback about which operations succeeded/failed
  • Maintain transaction-like behavior where possible

Output Requirements:

  • Provide complete, working tool implementations
  • Include proper TypeScript typing and imports
  • Follow established naming conventions
  • Include comprehensive parameter descriptions
  • Ensure tools are immediately usable by LLMs

You should prioritize creating tools that feel natural for LLMs to use while maintaining the robustness and type safety expected in this mature codebase. Always consider the LLM's perspective: what would be the most intuitive way to accomplish this task? Never leave any Typescript errors unsolved ALWAYS use the mcp-integration-test-creator to create integration tests for these tools

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. 7d ago First seen · 62 lines · 0 tokens per session scan A 09ff40fe4b5d

Subscribe to this mod's changes

mcp-tool-creator is an agent published in the GitHub repository umbraco/Umbraco-CMS-MCP-Dev (39 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 967 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens