mcp-tool-creator

mcp-tool-creator is an agent for Claude Code from umbraco/Umbraco-MCP-Base. It costs 39 tokens per session (1,254 once invoked), scanned A, original, MIT.

A coding assistant for creating Model Context Protocol (MCP) tools that connect language models to Umbraco APIs. It follows the project's toolkit and generated API-client patterns.

In plain words
What is it for?
Use it to design and implement MCP tools for Umbraco API endpoints, including tools for retrieving, listing, creating, updating, or deleting data.
Why use it?
It removes the need to design each tool interface and API connection from scratch. It also helps keep new tools consistent with the existing Umbraco MCP server.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { getYourAPI } from "../api/generated/yourApi.js";.

Part of the umbraco-mcp-skills plugin — 13 skills, 7 agents shipped together

Good fit Use it to design and implement MCP tools for Umbraco API endpoints, including tools for retrieving, listing, creating, updating, or deleting data.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/umbraco/Umbraco-MCP-Base
agentmods
npx agentmods add agents/umbraco/umbraco-mcp-base/mcp-tool-creator

Made for: Claude Code.

Or install umbraco-mcp-skills, the plugin that ships this one along with the rest of its 13 skills, 7 agents.

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-mcp-base/mcp-tool-creator/github.svg)](https://agentmods.dev/agents/umbraco/umbraco-mcp-base/mcp-tool-creator)
Your own site
<a href="https://agentmods.dev/agents/umbraco/umbraco-mcp-base/mcp-tool-creator"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-mcp-base/mcp-tool-creator/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.

agentmods 80×15 button for mcp-tool-creator

Your own site · 80×15
<a href="https://agentmods.dev/agents/umbraco/umbraco-mcp-base/mcp-tool-creator"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-mcp-base/mcp-tool-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,254 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 $0.00039 $0.01254
Opus 5 $0.00019 $0.00627
Sonnet 5 $0.00008 $0.00251
Haiku 4.5 $0.00004 $0.00125

Measured 12d ago against content hash 837b4d629cda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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.

plugins/umbraco-mcp-skills/agents/mcp-tool-creator.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert MCP tool architect specializing in creating Model Context Protocol tools using the @umbraco-cms/mcp-server-sdk. 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
  • Use the toolkit's helper functions consistently
  • Follow established patterns from the template project
  • Create tools that work seamlessly with Orval-generated clients

Technical Implementation

Tool Structure Pattern

All tools follow this pattern:

import {
  withStandardDecorators,
  executeGetApiCall,      // For GET single item
  executeGetItemsApiCall, // For GET collections/arrays (wraps response as { items })
  executeVoidApiCall,     // For DELETE/PUT operations
  createToolResult,       // For custom responses (CREATE)
  CAPTURE_RAW_HTTP_RESPONSE,
  ToolDefinition,
} from "@umbraco-cms/mcp-server-sdk";
import type { getYourAPI } from "../api/generated/yourApi.js";
import { yourInputSchema, yourOutputSchema } from "../api/generated/yourApi.zod.js";

type ApiClient = ReturnType<typeof getYourAPI>;

const YourTool = {
  name: "your-tool-name",
  description: "Clear description of what the tool does",
  inputSchema: yourInputSchema.shape,
  outputSchema: yourOutputSchema,  // For GET operations
  slices: ["read"],  // Tool categorization
  annotations: {
    readOnlyHint: true,  // For GET operations
  },
  handler: async ({ param }) => {
    return executeGetApiCall<ReturnType<ApiClient["methodName"]>, ApiClient>(
      (client) => client.methodName(param, CAPTURE_RAW_HTTP_RESPONSE)
    );
  },
} satisfies ToolDefinition<typeof yourInputSchema.shape, typeof yourOutputSchema>;

export default withStandardDecorators(YourTool);

Operation Type Patterns

GET single item (returns object):

  • Use executeGetApiCall
  • Add outputSchema
  • Set annotations: { readOnlyHint: true }
  • Set slices: ["read"]

Read the full file on GitHub · 131 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.

  1. 12d ago First seen · 131 lines · 39 tokens per session scan A 837b4d629cda

Subscribe to this mod's changes

mcp-tool-creator is an agent published in the GitHub repository umbraco/Umbraco-MCP-Base (2 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,254 once invoked, about $0.0002 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.

Related

Other agents, from other repositories